© 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. 12-TRANSCODER-HP
    7. 22587
    Prev
    Next
    INDEX
    Explanations

    stickers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¯æľĢ
    -0.27
    ertext
    -0.27
    iÅŁ
    -0.27
    _BUFF
    -0.26
    对æĪij们
    -0.26
    åIJĮèĥŀ
    -0.26
    _HOR
    -0.25
    é¼ĵèĪŀ
    -0.25
    æĺ¯æĪij们
    -0.24
    è¿·
    -0.24
    POSITIVE LOGITS
    çı¥
    0.27
    .fhir
    0.27
     trừ
    0.27
    afi
    0.25
    ends
    0.24
    .virtual
    0.24
    ä¸ĭæ²ī
    0.24
    èĻļæĭŁ
    0.24
     Pear
    0.24
    ulaire
    0.23
    Activations Density 0.029%

    No Known Activations