© 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. 8476
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĩĩ纳
    -0.29
    à®´
    -0.28
    lys
    -0.25
    à¸Ħà¸Ń
    -0.24
    hips
    -0.24
    .colorbar
    -0.24
    влек
    -0.24
    mut
    -0.24
    ÑİÑĤ
    -0.23
     luck
    -0.23
    POSITIVE LOGITS
     rather
    0.27
    èĢĮä¸įæĺ¯
    0.26
     Overs
    0.26
     principals
    0.26
     Riders
    0.25
    rather
    0.24
     governed
    0.24
    ãĥĨãĥ³
    0.24
    ourcing
    0.24
    ogenic
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.