© 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. 23884
    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
    robat
    -0.31
    scriptId
    -0.30
    çĥĻ
    -0.28
    缴éĢļ车
    -0.26
     blinds
    -0.26
    èĬ
    -0.26
    ettel
    -0.25
    ILITIES
    -0.25
     suff
    -0.25
    roach
    -0.25
    POSITIVE LOGITS
    ftar
    0.28
    (shape
    0.25
     PIE
    0.24
    [^
    0.24
     Pir
    0.24
    umpy
    0.24
    maal
    0.23
    pun
    0.23
    axed
    0.23
     holding
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.