© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62745
    Prev
    Next
    INDEX
    Explanations

    questions/answers

    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
    Negative Logits
    æľīå¤ļ大
    -0.47
    æľīåĵªäºĽ
    -0.44
    æľīå¤ļå°ij
    -0.41
    åĵªäºĽ
    -0.40
    æĢİ
    -0.39
    äºĨå¤ļå°ij
    -0.38
    ä½ķç§į
    -0.38
    æĢİæł·
    -0.38
    该å¦Ĥä½ķ
    -0.38
    å¦Ĥä½ķ
    -0.37
    POSITIVE LOGITS
    å°±æĺ¯åľ¨
    0.30
    _mgmt
    0.27
    -upper
    0.26
    ä¸įä¸Ĭ
    0.26
    -fw
    0.26
    rophe
    0.25
     Niet
    0.25
    åĩºåİĤ
    0.24
    umpt
    0.24
     sint
    0.24
    Activations Density 49.422%

    No Known Activations