© 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. 151256
    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
     shave
    -0.25
    æijĬ
    -0.25
    æĭĸ
    -0.25
     shove
    -0.24
    setUp
    -0.24
     drag
    -0.23
    .Builder
    -0.23
    elu
    -0.23
    imals
    -0.23
    currentColor
    -0.23
    POSITIVE LOGITS
    æĶ¶åĪ°äºĨ
    0.29
     subordinate
    0.27
    omite
    0.26
    è®°
    0.26
     refuse
    0.25
    å¿ĺè®°
    0.25
    thouse
    0.25
    认
    0.25
    _DENIED
    0.24
    æĥ³åĪ°äºĨ
    0.24
    Activations Density 1.347%

    No Known Activations

    This feature has no known activations.