© 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. 108564
    Prev
    Next
    INDEX
    Explanations

    some

    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
    åĪĨåĪ«æĺ¯
    -0.31
    handlers
    -0.31
    éĴ»çŁ³
    -0.26
    è¿ĻäºĽä¸ľè¥¿
    -0.26
     constituted
    -0.25
    ç»ĦæĪIJçļĦ
    -0.25
     ivory
    -0.25
    digits
    -0.25
    è¿ĻäºĽ
    -0.24
    objects
    -0.24
    POSITIVE LOGITS
     key
    0.34
    éĩįè¦ģ
    0.32
     important
    0.31
     essential
    0.29
     major
    0.28
     top
    0.28
    家åĸ»æĪ·æĻĵ
    0.28
     or
    0.28
    ÑĤоп
    0.27
    éĩįè¦ģçļĦ
    0.27
    Activations Density 0.898%

    No Known Activations