© 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. 42235
    Prev
    Next
    INDEX
    Explanations

    comparison words

    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
    .inflate
    -0.30
    è¿Ļå¥Ĺ
    -0.30
    ctal
    -0.27
    å¥Ĺ
    -0.27
    æī«
    -0.27
    _IF
    -0.26
    浪
    -0.26
    _cast
    -0.25
    èĢĥ
    -0.25
    è¯Ń
    -0.24
    POSITIVE LOGITS
     manipulation
    0.32
     acts
    0.31
     confirmation
    0.31
     infringement
    0.30
     simply
    0.29
     repayment
    0.29
     integration
    0.28
    acts
    0.28
    onomy
    0.28
     characterization
    0.28
    Activations Density 0.002%

    No Known Activations