© 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. 97783
    Prev
    Next
    INDEX
    Explanations

    an

    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
     WITHOUT
    -0.29
    æĪĸå¤ļ
    -0.28
    åİ»åģļ
    -0.27
    /an
    -0.26
    符åIJĪ
    -0.26
    /control
    -0.25
    ï¼Įé»ĺ认
    -0.25
    åģļ
    -0.25
    åĪĨè£Ĥ
    -0.24
    åħ¶ä¸Ńæľī
    -0.24
    POSITIVE LOGITS
     area
    0.39
     average
    0.38
     appeal
    0.37
     ideal
    0.36
     extreme
    0.36
     electric
    0.36
     arrangement
    0.35
     egg
    0.35
     additional
    0.35
     orientation
    0.35
    Activations Density 0.284%

    No Known Activations