© 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. 112129
    Prev
    Next
    INDEX
    Explanations

    a

    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
    窣
    -0.30
    ’n
    -0.25
    ç©¿æ¢Ń
    -0.25
    ç¼¢
    -0.23
    /Q
    -0.23
    _PREF
    -0.23
    embr
    -0.23
     Rem
    -0.23
     rim
    -0.23
    çĽ¸äº²
    -0.23
    POSITIVE LOGITS
    æijĨåľ¨
    0.29
    æķĸ
    0.27
     all
    0.26
    ten
    0.25
    ilon
    0.25
    æ¶Īéĺ²
    0.25
     different
    0.24
    riger
    0.24
    _attachment
    0.23
    弥补
    0.23
    Activations Density 0.035%

    No Known Activations