© 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. 130173
    Prev
    Next
    INDEX
    Explanations

    featured

    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
    èĩ£
    -0.31
     anyway
    -0.28
    pon
    -0.27
     and
    -0.27
     ...
    -0.26
     though
    -0.25
    âĢ¦âĢ¦
    -0.24
    encies
    -0.24
    ful
    -0.24
    istes
    -0.23
    POSITIVE LOGITS
    èĻIJå¾ħ
    0.27
     specializing
    0.25
    lâ
    0.25
    è°Ł
    0.25
    å¢ŀ设
    0.24
    æĭ¨æīĵ
    0.24
    è¯ķè¯ķ
    0.23
    repid
    0.23
    ä¸ĭæīĭ
    0.23
     unfolded
    0.23
    Activations Density 0.001%

    No Known Activations