© 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. 35-TRANSCODER-HP
    7. 39475
    Prev
    Next
    INDEX
    Explanations

    Chinese names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    territ
    -0.29
    å¹ķåIJİ
    -0.29
    ç¦ıåĪ©
    -0.28
     Welfare
    -0.27
    å¾ĹçĽĬ
    -0.27
    åıĤ
    -0.26
    PERT
    -0.26
    ãģ°ãģĭãĤĬ
    -0.26
    charge
    -0.26
    worthy
    -0.25
    POSITIVE LOGITS
    hog
    0.42
    hus
    0.40
    hip
    0.36
    hin
    0.36
    hos
    0.35
    hung
    0.34
    isu
    0.34
    hum
    0.33
    hash
    0.33
     hip
    0.33
    Activations Density 0.138%

    No Known Activations