© 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. 32-TRANSCODER-HP
    7. 43444
    Prev
    Next
    INDEX
    Explanations

    schizophrenia and mental health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅŁa
    -0.30
     nich
    -0.26
    inary
    -0.26
     Lv
    -0.25
     driv
    -0.25
    okies
    -0.25
     sürü
    -0.25
     Boutique
    -0.24
    .SerializeObject
    -0.24
     lig
    -0.24
    POSITIVE LOGITS
    bial
    0.28
    产åĵģè´¨éĩı
    0.27
    çĶ¨äºº
    0.27
    åĬŀ好
    0.27
    è´¨éĩıéĹ®é¢ĺ
    0.26
    estival
    0.25
    plevel
    0.25
    é«ĺæ°´å¹³
    0.24
    srv
    0.24
    æĬĵæįķ
    0.24
    Activations Density 0.013%

    No Known Activations