© 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. 23-TRANSCODER-HP
    7. 24175
    Prev
    Next
    INDEX
    Explanations

    website content and copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥĮ
    -0.30
    	trace
    -0.29
    æĦıåIJij
    -0.25
     precious
    -0.25
    Coding
    -0.25
    åĩłåĪĨ
    -0.25
    ~,
    -0.24
    ase
    -0.24
    ÑĥÑĪки
    -0.24
    çķª
    -0.24
    POSITIVE LOGITS
    uci
    0.25
    esis
    0.25
    lace
    0.25
     intellig
    0.24
    æīĢæıIJä¾Ľ
    0.24
    rence
    0.24
    odem
    0.24
    egen
    0.24
    çĶŁäº§æĢ»åĢ¼
    0.24
    UNT
    0.23
    Activations Density 0.013%

    No Known Activations