© 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. 19615
    Prev
    Next
    INDEX
    Explanations

    words ending in "ise"

    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
    usting
    -0.29
     corr
    -0.26
     gathering
    -0.25
    rupted
    -0.25
    Author
    -0.24
    кла
    -0.24
    uggested
    -0.24
    utors
    -0.24
    ök
    -0.24
     oy
    -0.23
    POSITIVE LOGITS
    ise
    0.31
    ISE
    0.30
    isen
    0.28
    dis
    0.28
    QP
    0.28
    çĿ¹
    0.28
    æ¤Ĵ
    0.27
    dt
    0.26
    Sizes
    0.26
    ints
    0.25
    Activations Density 0.046%

    No Known Activations