© 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. 33-TRANSCODER-HP
    7. 54351
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ´çIJĨ
    -0.27
    -direction
    -0.26
    /gallery
    -0.24
    _pattern
    -0.24
    .djangoproject
    -0.24
     táºŃn
    -0.24
    社ä¼ļæķĪçĽĬ
    -0.23
    .circular
    -0.23
    à¸Ńà¸Ń
    -0.23
    OperationException
    -0.23
    POSITIVE LOGITS
    |m
    0.28
    骥
    0.28
    horn
    0.28
    ми
    0.27
    ,content
    0.26
     blow
    0.25
    acons
    0.25
     f
    0.25
    eme
    0.24
    ãĥªãĤ¢
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.