© 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. 107427
    Prev
    Next
    INDEX
    Explanations

    changes in state

    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
    è¾Ī
    -0.29
    adin
    -0.26
    åºĶçĶ¨åľºæĻ¯
    -0.26
    ока
    -0.25
    Pane
    -0.25
    åĬ¨ä½ľ
    -0.25
    antes
    -0.24
    çļĦåºĶçĶ¨
    -0.24
    åĬĽåº¦
    -0.24
    mal
    -0.23
    POSITIVE LOGITS
    æĬ½
    0.29
    æµģåIJij
    0.27
     signatures
    0.27
    éģĵè·¯ä¸Ĭ
    0.27
    ocos
    0.25
    TECT
    0.25
    路边
    0.25
    _slope
    0.24
     Ive
    0.24
    onis
    0.24
    Activations Density 0.905%

    No Known Activations