© 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. 20-TRANSCODER-HP
    7. 141717
    Prev
    Next
    INDEX
    Explanations

    Assorted names/locations/Latin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    пÑĥÑģк
    -0.26
    >('
    -0.25
    ÃŃveis
    -0.24
    ë¦Ħ
    -0.24
    enos
    -0.24
    pill
    -0.24
    车ä¸Ĭ
    -0.23
    éĥ¨åĪĨåĨħ容
    -0.23
     relative
    -0.23
    çļĦåĨħ容
    -0.23
    POSITIVE LOGITS
    ycl
    0.29
    西路
    0.25
     Gamer
    0.24
    grown
    0.24
    .getLong
    0.23
     Ùħت
    0.23
    AppBundle
    0.23
     Rede
    0.23
    brick
    0.23
     growing
    0.23
    Activations Density 22.513%

    No Known Activations