© 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. 150058
    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
     react
    -0.27
     front
    -0.27
    infra
    -0.26
     Corinthians
    -0.26
     оÑĤз
    -0.25
    ÃŃs
    -0.25
    olio
    -0.25
    иÑĢовки
    -0.24
     lineno
    -0.24
    lei
    -0.24
    POSITIVE LOGITS
    çļĦèĥ½éĩı
    0.29
    ences
    0.28
    ursed
    0.27
    åĩºå¤Ħ
    0.26
    æħ¢æħ¢çļĦ
    0.26
     chatter
    0.26
    ä¸Ĭç½ij
    0.26
     hum
    0.26
     cref
    0.24
    ENCE
    0.24
    Activations Density 1.883%

    No Known Activations

    This feature has no known activations.