© 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. 151286
    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
    aption
    -0.25
    è¿Ł
    -0.25
    缸å½ĵ
    -0.24
    Delimiter
    -0.24
    licos
    -0.24
    à¸Ľà¸£à¸²à¸ģà¸ı
    -0.24
    æ¦Ĥ念
    -0.24
    çIJĨ解
    -0.24
     Blazers
    -0.24
    uckle
    -0.23
    POSITIVE LOGITS
    eded
    0.30
    eding
    0.26
    лÑıем
    0.25
    usk
    0.25
    vens
    0.25
     ours
    0.25
     Ñĥзн
    0.24
    羣çĪ±
    0.24
     Recon
    0.24
    -sama
    0.24
    Activations Density 3.378%

    No Known Activations

    This feature has no known activations.