© 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. 23103
    Prev
    Next
    INDEX
    Explanations

    against

    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
    åħ´å¥ĭ
    -0.29
    æ±Ĺ
    -0.26
    åĩºæ±Ĺ
    -0.26
    ãĤ¾
    -0.25
    åħ´
    -0.25
    aux
    -0.25
    èħĨ
    -0.25
    ä¸įç¦ģ
    -0.25
    æ±īæĹı
    -0.25
    į°
    -0.25
    POSITIVE LOGITS
    (Constructor
    0.28
    åľ¨äº¬
    0.27
    æĿĥéĩį
    0.26
     gram
    0.25
    маг
    0.25
    æ²īéĩį
    0.25
    ayload
    0.24
     Manuals
    0.24
    èĦ²
    0.24
    oder
    0.24
    Activations Density 0.002%

    No Known Activations