© 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. 43682
    Prev
    Next
    INDEX
    Explanations

    don

    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
    æĶ¶
    -0.27
    eness
    -0.26
    cc
    -0.25
     perman
    -0.24
    Blo
    -0.24
    ided
    -0.24
    ccd
    -0.24
    Äħd
    -0.24
     normal
    -0.24
    ÅĻ
    -0.24
    POSITIVE LOGITS
    inals
    0.31
    ération
    0.27
    fas
    0.27
    .fd
    0.25
    ÑĦик
    0.25
    кон
    0.25
    ufs
    0.25
    ãĥ¡ãĥ³ãĥĪ
    0.24
    kan
    0.24
    aldi
    0.24
    Activations Density 0.000%

    No Known Activations