© 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. 24021
    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
    ger
    -0.28
    çĥŃéĩı
    -0.26
    GER
    -0.26
    cka
    -0.26
     stakes
    -0.26
    propri
    -0.26
     Kidd
    -0.25
    anic
    -0.25
    unga
    -0.25
    ÑĥÑī
    -0.25
    POSITIVE LOGITS
    idle
    0.27
     land
    0.25
     mouths
    0.25
    land
    0.25
    æıĦ
    0.25
    大åŀĭ
    0.24
    lane
    0.24
    .land
    0.23
    称为
    0.23
    åı£å¤´
    0.23
    Activations Density 0.785%

    No Known Activations

    This feature has no known activations.