© 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. 12-TRANSCODER-HP
    7. 22777
    Prev
    Next
    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĶŁ
    -0.29
    kah
    -0.28
    åį¡æĭī
    -0.28
    ade
    -0.28
    Scalars
    -0.26
    iris
    -0.26
    ades
    -0.26
     studies
    -0.25
    FX
    -0.25
    Studies
    -0.25
    POSITIVE LOGITS
    å¦ĸ
    0.27
    delay
    0.26
    åIJij社ä¼ļ
    0.26
    دس
    0.25
    -inverse
    0.25
     Ghost
    0.24
    æľ¯è¯Ń
    0.24
     verso
    0.23
    ç«ŀä»·
    0.23
     thinly
    0.23
    Activations Density 0.000%

    No Known Activations