© 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. 43452
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     inform
    -0.30
    .Clock
    -0.28
    åĨį说
    -0.28
    ÇĶ
    -0.27
    她说
    -0.27
    åijĬ訴
    -0.27
     telling
    -0.27
     tell
    -0.27
    è¿Ļä¹Ī说
    -0.27
     phrase
    -0.26
    POSITIVE LOGITS
    _('
    0.31
    _='
    0.28
     goes
    0.28
     vows
    0.27
    åĭĭ
    0.26
    ä¸Ģæľµ
    0.26
    çªį
    0.25
    æĭĬ
    0.25
     went
    0.24
    ..'
    0.24
    Activations Density 0.008%

    No Known Activations