© 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. 25-TRANSCODER-HP
    7. 107678
    Prev
    Next
    INDEX
    Explanations

    Various topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨä¸Ģ份
    -0.29
     adel
    -0.25
    oton
    -0.24
    大家åĪĨ享
    -0.23
    posit
    -0.23
     paving
    -0.23
     Share
    -0.23
    æī®æ¼Ķ
    -0.23
    astically
    -0.23
    xdd
    -0.23
    POSITIVE LOGITS
    æ³ķ人
    0.29
     triá»ĩu
    0.24
    æīįçŁ¥éģĵ
    0.24
    夸
    0.24
    acy
    0.23
     Vern
    0.23
    erty
    0.23
    edy
    0.23
    ؤÙĪÙĦ
    0.23
    ystate
    0.23
    Activations Density 0.931%

    No Known Activations