© 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. 20-TRANSCODER-HP
    7. 130719
    Prev
    Next
    INDEX
    Explanations

    steril

    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
    Not in Any Lists

    No Comments

    Negative Logits
     wide
    -0.30
    -wide
    -0.30
    宽
    -0.27
    è¯ŀ
    -0.27
    éĺĶ
    -0.26
    壮
    -0.25
    ussian
    -0.24
    å¸ı
    -0.24
    idon
    -0.24
    tribute
    -0.23
    POSITIVE LOGITS
    ä¾Ŀ
    0.30
    åĿŃ
    0.26
     whore
    0.25
    çľ¼çļ®
    0.24
     cáºŃn
    0.24
     chois
    0.23
    å¤įåıij
    0.23
    æĬĬæĮģ
    0.23
    çļĦæĵįä½ľ
    0.23
    _stdio
    0.23
    Activations Density 11.194%

    No Known Activations