© 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. 25-TRANSCODER-HP
    7. 107785
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -shell
    -0.28
    shell
    -0.28
    req
    -0.28
     strokes
    -0.26
    çŁ¥éģĵèĩªå·±
    -0.26
    åīįè¿°
    -0.26
    оÑĩек
    -0.25
    riers
    -0.25
    setType
    -0.25
    sts
    -0.24
    POSITIVE LOGITS
    aravel
    0.27
    addAll
    0.26
    ifi
    0.26
    éģĩ
    0.24
    大éĻ¸
    0.24
     vieux
    0.23
    å¤©åºľ
    0.23
    ateur
    0.23
    åįģ足
    0.23
    æ¶Īéĺ²å®īåħ¨
    0.23
    Activations Density 4.813%

    No Known Activations