© 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. 22-TRANSCODER-HP
    7. 129419
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IOD
    -0.27
    èĩªçĶ±è´¸æĺĵ
    -0.24
    ãģĶ
    -0.24
    ä»ĭ
    -0.24
     sud
    -0.23
    èĥ³
    -0.23
     smack
    -0.23
    á»Ķ
    -0.23
    ected
    -0.23
     ENTRY
    -0.22
    POSITIVE LOGITS
     usability
    0.26
    ptic
    0.26
     Kart
    0.25
    adal
    0.25
    ported
    0.25
    åºŁ
    0.25
    çĤ¹äºĨ
    0.24
    æĵģ
    0.24
    æĭ¥
    0.24
     toxicity
    0.24
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.