© 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. 97651
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    icism
    -0.33
    otics
    -0.30
    æ°ijæĹıæĸĩåĮĸ
    -0.28
    èģĥ
    -0.27
    ymology
    -0.27
    大éģĵ
    -0.27
    路桥
    -0.27
    dür
    -0.27
    lds
    -0.26
    gnore
    -0.26
    POSITIVE LOGITS
    èĸĦ
    0.28
    å¾Ī
    0.28
    å¿«
    0.27
    Aud
    0.27
    缺
    0.27
    relevant
    0.27
    人群
    0.26
    break
    0.26
    Break
    0.25
     grues
    0.25
    Activations Density 0.002%

    No Known Activations