© 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. 9-TRANSCODER-HP
    7. 29759
    Prev
    Next
    INDEX
    Explanations

    proper nouns/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impro
    -0.33
    umn
    -0.31
    itre
    -0.27
    umm
    -0.27
    夹
    -0.26
    ãĥĶãĥ³
    -0.26
    æĪIJ年人
    -0.26
     retrie
    -0.26
    алÑĮно
    -0.26
     sơ
    -0.25
    POSITIVE LOGITS
    èĦĤ
    0.29
    鬼
    0.27
     wearing
    0.26
    bots
    0.25
    Strategy
    0.25
    æ±Ł
    0.25
    black
    0.24
     guards
    0.24
    Comment
    0.23
    :test
    0.23
    Activations Density 0.237%

    No Known Activations