© 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. 35-TRANSCODER-HP
    7. 39259
    Prev
    Next
    INDEX
    Explanations

    Mal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¢Ł
    -0.27
    ä¹į
    -0.26
    cosa
    -0.26
    ķĮ
    -0.25
     Ges
    -0.25
    æĿ¥è¯´
    -0.25
    bourne
    -0.25
     weaker
    -0.25
    anan
    -0.25
    æĮĩçļĦæĺ¯
    -0.25
    POSITIVE LOGITS
    å¯Ĩ
    0.32
    ç¼¢
    0.31
    ?url
    0.28
    ên
    0.27
    uzz
    0.26
    缪
    0.26
    è¦ģåģļåĪ°
    0.26
    даÑĤÑĮ
    0.26
    ÑģÑĤолÑĮ
    0.26
    Ø·ÙĨ
    0.24
    Activations Density 1.406%

    No Known Activations