© 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. 131048
    Prev
    Next
    INDEX
    Explanations

    def

    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
    aware
    -0.27
    _PO
    -0.26
    ificates
    -0.26
    poi
    -0.25
    uary
    -0.25
    å±Ģéķ¿
    -0.25
    otal
    -0.25
     biod
    -0.25
    æ³ī
    -0.24
    aight
    -0.24
    POSITIVE LOGITS
    cko
    0.32
    -peer
    0.29
    loys
    0.28
    Mocks
    0.25
     nämlich
    0.25
    _INCREMENT
    0.24
    æ¢ł
    0.24
     Association
    0.24
     Photographer
    0.23
     Mandal
    0.23
    Activations Density 4.456%

    No Known Activations