© 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. 40217
    Prev
    Next
    INDEX
    Explanations

    say "ending like -ating"

    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
    ç¢ĺ
    -0.28
     lords
    -0.27
    salt
    -0.27
     ruining
    -0.27
     barrels
    -0.26
     loudly
    -0.25
    ä¸įå¾Ĺå·²
    -0.25
    körper
    -0.25
     ridden
    -0.25
     GLsizei
    -0.24
    POSITIVE LOGITS
    au
    0.40
    ai
    0.40
    an
    0.36
    ame
    0.36
    айÑĤе
    0.35
    ahan
    0.35
    ata
    0.35
    ape
    0.35
    aje
    0.35
    atio
    0.35
    Activations Density 35.344%

    No Known Activations