© 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. 130547
    Prev
    Next
    INDEX
    Explanations

    be

    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
     Äijá»ĭnh
    -0.26
    çļĦæķ°æį®
    -0.26
    marked
    -0.25
    çݺ
    -0.25
    CAC
    -0.25
    åľ¨æľªæĿ¥
    -0.25
    plates
    -0.25
    èles
    -0.24
     stakes
    -0.24
    caled
    -0.24
    POSITIVE LOGITS
    "--
    0.30
    avan
    0.26
     Frankfurt
    0.25
    [--
    0.24
    顺çĿĢ
    0.24
     consider
    0.24
    æģ¨ä¸įå¾Ĺ
    0.24
    大家åĪĨ享
    0.24
     Åģa
    0.24
    apult
    0.23
    Activations Density 11.329%

    No Known Activations