© 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. 23422
    Prev
    Next
    INDEX
    Explanations

    Names and locations

    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
    åľ¨ä¸Ĭæµ·
    -0.27
    river
    -0.27
    esson
    -0.27
    人åı£
    -0.25
    Fx
    -0.25
    çļĦ帮åĬ©
    -0.25
    ressed
    -0.24
     plate
    -0.24
     resisted
    -0.24
    OLA
    -0.24
    POSITIVE LOGITS
    иÑĢоваÑĤÑĮ
    0.26
    åĪĹ
    0.26
    Ÿ
    0.25
     sourceMappingURL
    0.25
    .feed
    0.24
    sWith
    0.24
    ä¸ĵåijĺ
    0.23
     Rank
    0.23
    éĩijåĪļ
    0.23
     pro
    0.23
    Activations Density 0.000%

    No Known Activations