© 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. 41297
    Prev
    Next
    INDEX
    Explanations

    the

    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
    angan
    -0.28
    ноÑģÑĤ
    -0.28
     noqa
    -0.26
    帧
    -0.25
    çªij
    -0.24
    çĩ¥
    -0.24
    ESS
    -0.24
    kÄĻ
    -0.23
    èĬ¸
    -0.23
    xAF
    -0.23
    POSITIVE LOGITS
    erna
    0.28
    åŃŁ
    0.27
     pinch
    0.27
     Panama
    0.27
    为æĬĵ
    0.25
    abler
    0.25
     Home
    0.25
     home
    0.25
    undance
    0.25
    éĥ¨ä¸»ä»»
    0.25
    Activations Density 0.001%

    No Known Activations