© 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. 42193
    Prev
    Next
    INDEX
    Explanations

    Technical/research writing

    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
     Gros
    -0.30
     Rein
    -0.26
    ä¸ĬãģĴ
    -0.26
    oque
    -0.26
    ennie
    -0.25
    Animate
    -0.25
     Booth
    -0.25
    ropri
    -0.25
    isted
    -0.24
    åŃĺ
    -0.24
    POSITIVE LOGITS
     operational
    0.39
     Operational
    0.36
     estimated
    0.31
     Estimated
    0.30
    èĢĥå¯Ł
    0.28
     capital
    0.27
     invariant
    0.26
    æĭĵå±ķ
    0.26
    estimated
    0.26
     tests
    0.26
    Activations Density 0.001%

    No Known Activations