© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9003
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possibilities
    -0.50
     considerations
    -0.49
     readings
    -0.48
     policies
    -0.47
     divisions
    -0.46
     parties
    -0.45
     bearings
    -0.45
     speeches
    -0.45
     figures
    -0.45
     episodes
    -0.45
    POSITIVE LOGITS
    æĢģ度
    0.26
    ä¸ĢåłĨ
    0.25
    åı«
    0.25
    äºĨ大éĩıçļĦ
    0.25
    äºĴéĢļ
    0.25
     dataset
    0.24
    istor
    0.24
    çļĦ人éĥ½
    0.24
    inion
    0.24
     basis
    0.24
    Activations Density 0.000%

    No Known Activations