© 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. 111925
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
     Chron
    -0.27
    太å¤ļäºĨ
    -0.26
     unw
    -0.25
     whole
    -0.25
     apost
    -0.25
    åŁºæķ°
    -0.25
    gin
    -0.24
    çijŁ
    -0.24
     side
    -0.24
    è¹Ħ
    -0.24
    POSITIVE LOGITS
    iage
    0.29
    éĽķå¡ij
    0.27
    fiber
    0.26
    inth
    0.25
    anter
    0.25
    ĥģ
    0.25
     logfile
    0.25
    åľ¨åĵªéĩĮ
    0.24
    orer
    0.24
    aleb
    0.24
    Activations Density 0.010%

    No Known Activations