© 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. 35-TRANSCODER-HP
    7. 39703
    Prev
    Next
    INDEX
    Explanations

    French language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    statement
    -0.27
    enate
    -0.26
    edith
    -0.25
    äºĶè¡Į
    -0.25
    GraphQL
    -0.24
     Skywalker
    -0.24
    slick
    -0.24
    dden
    -0.24
    aken
    -0.24
    .Callback
    -0.24
    POSITIVE LOGITS
     aure
    0.30
    iqué
    0.25
    åħļé£İ
    0.25
    ée
    0.25
     inoc
    0.24
    ÃĥO
    0.24
     zwiÄħzane
    0.24
    ÅĤam
    0.24
    ToFront
    0.24
    öz
    0.23
    Activations Density 2.695%

    No Known Activations