© 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. 88134
    Prev
    Next
    INDEX
    Explanations

    им

    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
    ób
    -0.34
    ä¸Ģä½ĵ
    -0.27
    egr
    -0.27
    gaard
    -0.27
     Grammar
    -0.27
    rei
    -0.26
    oteca
    -0.25
    osite
    -0.25
    omics
    -0.25
    -safe
    -0.25
    POSITIVE LOGITS
    Combined
    0.26
    客è§Ĥ
    0.26
     amp
    0.25
    lim
    0.25
     rad
    0.25
    æļĤ
    0.25
    am
    0.24
     preliminary
    0.24
    è¿ĺæĺ¯ä¼ļ
    0.24
     somewhat
    0.24
    Activations Density 0.004%

    No Known Activations