© 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. 23-TRANSCODER-HP
    7. 24074
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    讲æķħäºĭ
    -0.27
    ntag
    -0.26
    WithValue
    -0.26
    æŃĮæīĭ
    -0.25
    åĶ±æŃĮ
    -0.25
    Reviewed
    -0.25
    cação
    -0.25
    usta
    -0.25
     Mandal
    -0.25
    Alternate
    -0.25
    POSITIVE LOGITS
    éĿ¢åīį
    0.28
    å±Ī
    0.27
     assigned
    0.26
    çªĴ
    0.26
     FPS
    0.25
    (integer
    0.25
    .Ma
    0.25
    RFC
    0.25
    ysql
    0.25
     Ne
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.