© 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. 87205
    Prev
    Next
    INDEX
    Explanations

    I

    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
    orrent
    -0.28
    seealso
    -0.26
    认åIJĮ
    -0.26
    äº²çľ¼
    -0.26
    好å¥ĩå¿ĥ
    -0.25
     appeals
    -0.25
    must
    -0.25
    orama
    -0.24
     Observation
    -0.24
    ãģ¤ãĤĤãĤĬ
    -0.24
    POSITIVE LOGITS
    нÑĮ
    0.28
    æĺ¯åIJ¦æľī
    0.26
    æĺ¯åIJ¦
    0.26
    #####
    0.26
    ####↵
    0.26
    ä¸ŃåĽ½å¸Ĥåľº
    0.25
    ledge
    0.25
    whether
    0.25
    Ø®Ùģ
    0.24
    (Player
    0.24
    Activations Density 0.017%

    No Known Activations