© 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. 98824
    Prev
    Next
    INDEX
    Explanations

    mandatory

    np_max-act · gemini-2.0-flash
    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
     Blanc
    -0.28
    æŁĦ
    -0.27
    åĹĵåŃIJ
    -0.26
    .SetActive
    -0.25
    ARA
    -0.24
    .generated
    -0.24
    antry
    -0.24
    æĨİ
    -0.23
    æ¯ĽåĪ©çİĩ
    -0.23
    ophage
    -0.23
    POSITIVE LOGITS
     aspects
    0.28
    ly
    0.27
    æĸ¹éĿ¢
    0.27
    adle
    0.26
     Sof
    0.26
     aspect
    0.26
     by
    0.25
     Aspect
    0.25
     downs
    0.25
     yet
    0.25
    Activations Density 0.044%

    No Known Activations