© 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. 108255
    Prev
    Next
    INDEX
    Explanations

    de

    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
    æµ·å¤ĸå¸Ĥåľº
    -0.26
     kald
    -0.25
    igy
    -0.25
     Kashmir
    -0.25
    åı»
    -0.24
    dur
    -0.24
     grate
    -0.24
     slugg
    -0.24
     clearfix
    -0.24
    nan
    -0.24
    POSITIVE LOGITS
    ä¸Ģ天
    0.29
    个ä½ĵ
    0.29
    çıł
    0.29
    常è§Ħ
    0.28
     TL
    0.28
    çħ§
    0.26
    ä½ĵä¼ļ
    0.26
    ç«łèĬĤ
    0.26
    ä¸Ģ个人
    0.25
     Individuals
    0.25
    Activations Density 0.110%

    No Known Activations