© 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. 57060
    Prev
    Next
    INDEX
    Explanations

    Code/Copyright text

    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
     Predict
    -0.25
    ç½ij约
    -0.25
    _frames
    -0.25
     FirebaseFirestore
    -0.24
    leen
    -0.24
     Liqu
    -0.24
    Ľå»º
    -0.24
    æŃ·
    -0.24
    oeff
    -0.23
    leccion
    -0.23
    POSITIVE LOGITS
     enumerated
    0.26
    _aff
    0.26
    iết
    0.26
    éĿĴ
    0.25
    omy
    0.24
     Ung
    0.24
    Anywhere
    0.24
    REAL
    0.24
     MATERIAL
    0.24
     tal
    0.24
    Activations Density 0.000%

    No Known Activations