© 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. 33-TRANSCODER-HP
    7. 53340
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ķ
    -0.33
     Trial
    -0.30
    æĬ¤
    -0.29
    Trial
    -0.29
     trial
    -0.28
    -employed
    -0.26
    trial
    -0.26
    boolean
    -0.26
     Boolean
    -0.25
     nale
    -0.25
    POSITIVE LOGITS
     gate
    0.33
    Attention
    0.30
    éģĵ
    0.30
    obra
    0.28
    主管
    0.28
    å¡«åĨĻ
    0.27
     Gate
    0.27
     Gateway
    0.26
    éŨ
    0.26
    odb
    0.25
    Activations Density 0.192%

    No Known Activations