© 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. 24445
    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
     <!--[
    -0.28
    被æ·ĺæ±°
    -0.26
    .Helper
    -0.26
    æĵį
    -0.26
    å¾Ĺèµ·
    -0.25
    ·»
    -0.25
    äºĨå¤ļå°ij
    -0.24
    TEX
    -0.23
    но
    -0.23
     HALF
    -0.23
    POSITIVE LOGITS
    æıı
    0.31
    æĬ±
    0.30
     Amb
    0.26
    echa
    0.26
    çŀ¬
    0.26
    XL
    0.25
    å¡ij
    0.25
    çĦ¦
    0.25
    线ä¸Ĭ线ä¸ĭ
    0.25
    ulis
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.