© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40402
    Prev
    Next
    INDEX
    Explanations

    geriatric care

    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
     RB
    -0.27
     conjug
    -0.27
     Shak
    -0.27
    icie
    -0.27
    dia
    -0.26
    jah
    -0.25
     Ful
    -0.24
     QB
    -0.24
     RG
    -0.24
    acers
    -0.24
    POSITIVE LOGITS
    opa
    0.36
    ops
    0.35
    om
    0.33
    ophil
    0.32
    oven
    0.32
    otel
    0.32
    oped
    0.32
     mill
    0.31
    opp
    0.30
    omp
    0.29
    Activations Density 0.006%

    No Known Activations