© 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. 43192
    Prev
    Next
    INDEX
    Explanations

    to

    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
    .flag
    -0.28
    PIP
    -0.28
    é¾Ļ
    -0.27
     Drill
    -0.27
    rud
    -0.27
     drill
    -0.26
    é¾į
    -0.26
    åºł
    -0.25
     drift
    -0.25
    éĴ»
    -0.25
    POSITIVE LOGITS
    å®ŀ
    0.27
    æľ¯
    0.26
    /pdf
    0.26
    åı£æľį
    0.25
     Operations
    0.24
     UC
    0.24
    operations
    0.24
     Mem
    0.24
     operations
    0.24
     confer
    0.24
    Activations Density 0.004%

    No Known Activations