© 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. 22-TRANSCODER-HP
    7. 87250
    Prev
    Next
    INDEX
    Explanations

    told

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĮľæĥ³
    -0.40
    认为
    -0.35
     conject
    -0.32
    ä»ĸ认为
    -0.32
    çĮľæµĭ
    -0.31
     theory
    -0.30
    æĪij认为
    -0.30
    æĪij们认为
    -0.30
    èĩĨ
    -0.29
     claimed
    -0.28
    POSITIVE LOGITS
    çİ°åĩº
    0.29
    rops
    0.27
    reeze
    0.25
    ç§Ń
    0.25
    _Ref
    0.25
     clearly
    0.24
    ä¸įå¾Ĺä¸į
    0.23
    ÑģÑĤÑĢел
    0.23
     spot
    0.23
    ees
    0.23
    Activations Density 0.000%

    No Known Activations