© 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. 130415
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    Dub
    -0.25
    oub
    -0.25
    æľĢåĪĿ
    -0.24
    Ĥ¤
    -0.24
    éĽ
    -0.24
     afflicted
    -0.24
    ee
    -0.23
    åĴª
    -0.23
    fact
    -0.23
     exerc
    -0.23
    POSITIVE LOGITS
    isoft
    0.27
    ushman
    0.27
     elgg
    0.25
    æĹłç¼ĺ
    0.25
     unins
    0.24
     mrb
    0.24
    æļĸå¿ĥ
    0.24
    opsis
    0.24
    åį«è§Ĩ
    0.23
    éķ¿èĢģ
    0.23
    Activations Density 0.022%

    No Known Activations