© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150308
    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
    å¢ĥ
    -0.31
    温
    -0.28
    zend
    -0.27
    ringe
    -0.26
    å¢ĥåĨħ
    -0.25
    osas
    -0.25
    lung
    -0.24
    ORK
    -0.24
     plais
    -0.23
     ji
    -0.23
    POSITIVE LOGITS
    ctp
    0.27
     Morse
    0.27
     champions
    0.26
     shielding
    0.25
     tool
    0.25
     shields
    0.24
     leveled
    0.24
    ailable
    0.24
    NOWLED
    0.24
    ayer
    0.23
    Activations Density 1.126%

    No Known Activations

    This feature has no known activations.