© 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. 42276
    Prev
    Next
    INDEX
    Explanations

    say ":/"

    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
     those
    -0.25
     yes
    -0.25
    æ¦Ĥ念
    -0.24
    éĤ®ç®±
    -0.24
    posables
    -0.24
    pus
    -0.24
     concept
    -0.23
    åĬ¨éĿĻ
    -0.23
    pop
    -0.23
    Those
    -0.23
    POSITIVE LOGITS
    ://
    0.92
    :/
    0.84
    :\
    0.75
    ://'
    0.71
    ://"
    0.70
    :///
    0.67
    ://{
    0.66
    :\\
    0.66
    ://${
    0.61
    ://%
    0.60
    Activations Density 0.055%

    No Known Activations