© 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. 43472
    Prev
    Next
    INDEX
    Explanations

    chemical contexts

    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
     Soph
    -0.29
    ctr
    -0.28
    itary
    -0.27
     rec
    -0.27
     Run
    -0.26
     Ku
    -0.25
    GER
    -0.25
    çijŀ
    -0.25
     Rec
    -0.25
    pr
    -0.24
    POSITIVE LOGITS
    china
    0.28
    ags
    0.26
    çİī
    0.26
     Elli
    0.25
    hydrate
    0.25
    ias
    0.25
    _lat
    0.25
    å¹´å¹´åºķ
    0.24
    į°
    0.23
    auty
    0.23
    Activations Density 0.003%

    No Known Activations