© 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. 129528
    Prev
    Next
    INDEX
    Explanations

    historical/location text snippets

    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
    ouri
    -0.33
    ä¸įæĿ¥
    -0.28
    ä¸į便
    -0.28
     gl
    -0.28
    ķĮ
    -0.26
    å¹²ä»Ģä¹Ī
    -0.26
    车ä¸Ĭ
    -0.25
     forward
    -0.25
    üst
    -0.25
     come
    -0.25
    POSITIVE LOGITS
    .tp
    0.25
     exploding
    0.25
    REAK
    0.25
    ndl
    0.25
    åľ¨äº¬
    0.24
    亿åIJ¨
    0.24
    ULE
    0.24
    initely
    0.24
     apocalypse
    0.24
    elta
    0.24
    Activations Density 0.008%

    No Known Activations