© 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. 107116
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     </>↵
    -0.31
    plier
    -0.29
    elier
    -0.28
    ÑĤÑĢо
    -0.27
    æī¾
    -0.25
    :";↵
    -0.25
    å»ºè®¾é¡¹çĽ®
    -0.25
    :');↵
    -0.24
    Stick
    -0.24
    -equ
    -0.24
    POSITIVE LOGITS
    ÑĤай
    0.28
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.28
     tall
    0.27
     Tall
    0.27
     appropriate
    0.25
     REVIEW
    0.25
     Lan
    0.24
     followed
    0.24
     Colt
    0.24
    ä½łåĸľæ¬¢
    0.24
    Activations Density 2.358%

    No Known Activations