© 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. 24-TRANSCODER-HP
    7. 149475
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     orm
    -0.31
    çĮ·
    -0.27
     Tight
    -0.26
     tightly
    -0.26
    æĸ¹å¼ıè¿Ľè¡Į
    -0.26
    æĥij
    -0.25
     politics
    -0.24
     tight
    -0.24
    ç´§
    -0.24
    Trying
    -0.23
    POSITIVE LOGITS
    æŶè£ħ
    0.25
    .cancel
    0.24
    ạt
    0.24
    elper
    0.24
    eria
    0.24
     cure
    0.23
    éħ¸å¥¶
    0.23
    wd
    0.23
    è¾ĵ
    0.23
     neger
    0.23
    Activations Density 0.981%

    No Known Activations

    This feature has no known activations.