© 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. 129889
    Prev
    Next
    INDEX
    Explanations

    inside

    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
    é£İéĻ©ç®¡çIJĨ
    -0.29
    _IOC
    -0.27
    chio
    -0.26
    .hm
    -0.25
    ç»Ļä½łä»¬
    -0.25
    å¼ĢèĬ±
    -0.24
     renamed
    -0.24
    è¶³å¤Ł
    -0.24
     nämlich
    -0.23
     enough
    -0.23
    POSITIVE LOGITS
    ä½ij
    0.30
    驱
    0.28
    ipers
    0.27
    ä¼¼ä¹İæĺ¯
    0.25
    noDB
    0.25
    çĿ¡
    0.24
    elden
    0.24
    OLUTION
    0.24
    ä¼¼ä¹İ
    0.24
    domain
    0.24
    Activations Density 0.001%

    No Known Activations