© 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. 151320
    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
    Negative Logits
    -fire
    -0.30
    çģ«çģ¾
    -0.28
    /fire
    -0.28
    ictim
    -0.26
     fireplace
    -0.26
    ahlen
    -0.25
    pref
    -0.25
    ñe
    -0.25
    dff
    -0.25
    odem
    -0.25
    POSITIVE LOGITS
    æŀĿ
    0.27
    ä¸Ģæīĭ
    0.26
    /apt
    0.25
    æķĪæŀľ
    0.24
    ç«Ļ
    0.24
     tilted
    0.24
     gaz
    0.24
    ears
    0.24
     told
    0.24
    APT
    0.24
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.