© 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. 20-TRANSCODER-HP
    7. 106982
    Prev
    Next
    INDEX
    Explanations

    math and computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exactly
    -0.31
     form
    -0.27
    umber
    -0.27
     careers
    -0.26
     exact
    -0.26
    ç¥ĸ
    -0.26
    ande
    -0.25
    åıĤ
    -0.24
    ource
    -0.24
    ores
    -0.24
    POSITIVE LOGITS
    fav
    0.27
    âĢ¦↵↵↵↵
    0.26
    abyrin
    0.25
    plen
    0.25
    们çļĦ
    0.25
    åıĪè¦ģ
    0.25
    itional
    0.24
    ä»įå°Ĩ
    0.24
     пÑĢеимÑĥÑīеÑģÑĤв
    0.24
    },'
    0.24
    Activations Density 28.209%

    No Known Activations