© 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. 30-TRANSCODER-HP
    7. 96455
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     machine
    -0.26
    -machine
    -0.25
     Machine
    -0.24
    çŃ¹éĽĨ
    -0.24
    uer
    -0.24
    кла
    -0.24
    variants
    -0.24
    Machine
    -0.24
    Means
    -0.24
     bursting
    -0.24
    POSITIVE LOGITS
    rene
    0.25
    åIJ¬è¯´
    0.25
    åĬŁå¤«
    0.24
    ìĦ±
    0.24
    æľįåĬ¡æ°´å¹³
    0.24
    éĻįåĪ°
    0.24
    (primary
    0.24
    primary
    0.24
    æ··
    0.24
     giỼi
    0.24
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.