© 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. 41990
    Prev
    Next
    INDEX
    Explanations

    Int

    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
     parach
    -0.26
     break
    -0.26
    ainless
    -0.26
     pragma
    -0.26
    .getMap
    -0.26
    ket
    -0.24
     Seal
    -0.24
    å°ģ
    -0.23
    CTYPE
    -0.23
    -round
    -0.23
    POSITIVE LOGITS
    .hd
    0.28
     orth
    0.28
    HD
    0.27
     Patri
    0.27
    icer
    0.27
    ox
    0.26
    olume
    0.25
    æľĪæľ«
    0.25
    imat
    0.25
    HAM
    0.25
    Activations Density 0.004%

    No Known Activations