© 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. 22-TRANSCODER-HP
    7. 112216
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Livingston
    -0.27
    cratch
    -0.26
    éļĶ
    -0.26
    åĽĽçº§
    -0.26
    illery
    -0.26
    å¿ĥ缮ä¸Ń
    -0.26
     presumed
    -0.25
    èIJĥ
    -0.25
    å±¥
    -0.25
    -sk
    -0.25
    POSITIVE LOGITS
    è¡Ķ
    0.29
    "${
    0.28
    rig
    0.27
    骥
    0.26
    ult
    0.25
    odka
    0.25
    bones
    0.25
     aides
    0.25
    _'.$
    0.24
    mant
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.