© 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. 42636
    Prev
    Next
    INDEX
    Explanations

    Technical/Academic texts

    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
    çĶŁçī©åѦ
    -0.33
    æıĸ
    -0.32
     Tits
    -0.28
    åŃ³
    -0.28
     Ih
    -0.27
    ä¸Ńåįİæ°ijæĹı
    -0.25
    oa
    -0.25
    ishi
    -0.25
     biological
    -0.25
    زÙĪ
    -0.25
    POSITIVE LOGITS
    ine
    0.26
    Member
    0.26
    _member
    0.25
    èİŀ
    0.24
    纨
    0.24
     Dom
    0.24
    ilot
    0.24
    .Member
    0.24
    anden
    0.23
     паÑĢа
    0.23
    Activations Density 0.000%

    No Known Activations