© 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. 8642
    Prev
    Next
    INDEX
    Explanations

    Ind

    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
    BS
    -0.27
    bs
    -0.24
    xad
    -0.24
    åıĪèĥ½
    -0.23
    å¸
    -0.23
     vague
    -0.23
    æ±²
    -0.23
    æ½ľåľ¨
    -0.22
     afore
    -0.22
    eland
    -0.22
    POSITIVE LOGITS
    hardt
    0.32
    .done
    0.27
    ìĹĦ
    0.27
     Dependency
    0.26
    omy
    0.25
    主æĦı
    0.25
    ä¸įå¦Ĥ
    0.25
    amat
    0.25
     Done
    0.25
    èĬ¥
    0.24
    Activations Density 1.103%

    No Known Activations