© 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. 31-TRANSCODER-HP
    7. 18094
    Prev
    Next
    INDEX
    Explanations

    intens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİŁæĸĩåľ°åĿĢ
    -0.29
    íĨł
    -0.25
    oined
    -0.25
    ONTAL
    -0.24
     syst
    -0.24
    寥
    -0.24
    ©½
    -0.24
    åĬłçĽŁ
    -0.24
    onces
    -0.24
    joint
    -0.24
    POSITIVE LOGITS
    ive
    0.34
    eness
    0.30
    acre
    0.30
     useClass
    0.29
    ives
    0.29
    hev
    0.28
    æĢ§çļĦ
    0.27
    ification
    0.26
    idade
    0.26
    enan
    0.26
    Activations Density 0.005%

    No Known Activations