© 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. 107984
    Prev
    Next
    INDEX
    Explanations

    say number

    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
    ä¸Ĭå¹´
    -0.28
     полов
    -0.27
    èĩªè±ª
    -0.27
    igs
    -0.27
    -pane
    -0.26
    åıĤ
    -0.25
    çļĦä¸Ģéĥ¨åĪĨ
    -0.24
     PAY
    -0.24
     pan
    -0.24
    æĪ¶
    -0.24
    POSITIVE LOGITS
     procure
    0.27
     дело
    0.25
    imore
    0.24
    ).__
    0.24
    å¤ļä½Ļ
    0.24
    elps
    0.24
    æīĩ
    0.23
    mor
    0.23
     Funds
    0.23
     ~(
    0.23
    Activations Density 0.899%

    No Known Activations