© 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. 97466
    Prev
    Next
    INDEX
    Explanations

    Copyright

    np_max-act · gemini-2.0-flash
    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
    lig
    -0.29
    iac
    -0.28
    geois
    -0.28
    .twitch
    -0.27
    .GetComponent
    -0.26
    lut
    -0.26
     ch
    -0.26
    leased
    -0.26
     errorCallback
    -0.26
    lic
    -0.25
    POSITIVE LOGITS
    çİ°åĩº
    0.29
    atre
    0.28
    åĪĥ
    0.27
    ETS
    0.26
    èĽĩ
    0.26
    æŶéĹ´ä¸º
    0.26
    ä¸¥æł¼çļĦ
    0.26
    çĺŁ
    0.26
     asn
    0.26
    ç³ľ
    0.26
    Activations Density 0.005%

    No Known Activations