© 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. 31-TRANSCODER-HP
    7. 19073
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįĥéĩĮ
    -0.30
    åŬ
    -0.28
     æĽ
    -0.28
    æľįåĬ¡å¹³åı°
    -0.26
    éĢĢåĽŀ
    -0.26
    uces
    -0.26
    èĩªçĦ¶æĺ¯
    -0.25
    ç»İ
    -0.25
    å¾Ĺ天
    -0.25
     META
    -0.25
    POSITIVE LOGITS
    -basket
    0.27
    è§Ĵ
    0.26
    0
    0.26
    èµĦ
    0.25
    _ary
    0.25
     Mavericks
    0.24
    æ¹Ľ
    0.23
     QTableWidgetItem
    0.23
    æĬĬæı¡
    0.23
    angi
    0.23
    Activations Density 2.416%

    No Known Activations