© 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. 107326
    Prev
    Next
    INDEX
    Explanations

    from

    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
    åħ¶ä»ĸçļĦ
    -0.33
    :?
    -0.28
    çĪ±ç¾İ
    -0.27
    æĿ³
    -0.27
    æīĢ产çĶŁçļĦ
    -0.26
    çļĦè¯Ŀé¢ĺ
    -0.25
    åħ·ä½ĵçļĦ
    -0.25
    :The
    -0.25
    ç»ıåħ¸çļĦ
    -0.24
    æīĢ
    -0.24
    POSITIVE LOGITS
     same
    0.50
    same
    0.40
     largest
    0.36
     latest
    0.35
     website
    0.33
     entire
    0.32
     entirety
    0.31
     vicinity
    0.30
     portion
    0.30
     solution
    0.30
    Activations Density 3.382%

    No Known Activations