© 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. 63096
    Prev
    Next
    INDEX
    Explanations

    in

    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
    åIJĥçļĦ
    -0.26
    awa
    -0.26
    _sha
    -0.26
    çºĮ
    -0.26
     rest
    -0.26
    éģ£
    -0.25
     resumes
    -0.25
     afterward
    -0.24
    æłĩéħį
    -0.24
    ìħĢ
    -0.24
    POSITIVE LOGITS
     instead
    0.35
     Instead
    0.30
    instead
    0.30
     ÑģамоÑģÑĤоÑı
    0.28
    /ns
    0.28
    Instead
    0.27
    NS
    0.26
    ]|[
    0.25
    宪
    0.24
    ãĤĤãģ£ãģ¨
    0.24
    Activations Density 88.179%

    No Known Activations