© 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. 141248
    Prev
    Next
    INDEX
    Explanations

    Scientific contexts with prepositions

    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
    æĭħ
    -0.30
    缸éĢļ
    -0.26
    KEN
    -0.26
    urr
    -0.26
    vel
    -0.24
    unar
    -0.24
    uC
    -0.23
    odem
    -0.23
    (Label
    -0.23
    åıĤè§Ĥ
    -0.23
    POSITIVE LOGITS
     ActionTypes
    0.28
    idget
    0.26
    overs
    0.26
     oversh
    0.26
     gsl
    0.24
     partitions
    0.24
    iless
    0.24
    #ga
    0.23
    èĢģå®ŀ
    0.23
    atories
    0.23
    Activations Density 8.022%

    No Known Activations