© 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. 149943
    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
     Subject
    -0.26
     subjects
    -0.26
     professors
    -0.25
     Morr
    -0.25
    .bounds
    -0.25
     Emp
    -0.25
     Subjects
    -0.24
    ICI
    -0.24
    subjects
    -0.24
     Ihren
    -0.24
    POSITIVE LOGITS
    æĸ°åĮº
    0.26
    gom
    0.26
    çİ°éĩij
    0.26
    åĽ½éĻħæľºåľº
    0.25
     seri
    0.25
    die
    0.25
    ç»Ń
    0.24
    egen
    0.23
     sealing
    0.23
    åĢĻéĢī
    0.23
    Activations Density 0.346%

    No Known Activations

    This feature has no known activations.