© 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. 97482
    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
     Force
    -0.32
     Story
    -0.26
    anonymous
    -0.26
    arella
    -0.25
    iol
    -0.25
     delta
    -0.24
     Version
    -0.23
     force
    -0.23
    anner
    -0.22
     Delta
    -0.22
    POSITIVE LOGITS
    les
    0.28
    亲çĪ±
    0.27
     mente
    0.27
    è¡¥
    0.26
    ä¸Ģæīĭ
    0.25
    let
    0.25
    éĩĬ
    0.25
    edic
    0.25
    åı¯èĥ½
    0.24
    plex
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.