© 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. 43024
    Prev
    Next
    INDEX
    Explanations

    code/data structures

    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
    ç²Ŀ
    -0.27
    ocup
    -0.27
    olith
    -0.26
     appropriation
    -0.25
    ebb
    -0.25
    ocado
    -0.25
    龸
    -0.24
     dynamic
    -0.24
     residue
    -0.23
    enment
    -0.23
    POSITIVE LOGITS
     indexes
    0.27
    ç´¢
    0.26
    ä¾Ĺ
    0.26
    ini
    0.25
    ï
    0.24
    å¹Ĥ
    0.24
    agra
    0.24
    fi
    0.24
    æ°´å¹³
    0.24
    è¡Ģ液循çݯ
    0.24
    Activations Density 0.004%

    No Known Activations