© 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. 108069
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     process
    -0.33
    -process
    -0.33
    process
    -0.32
    procedure
    -0.29
     procedure
    -0.29
     competit
    -0.29
    è¿ĩç¨ĭ
    -0.27
    	process
    -0.26
    ylan
    -0.26
    vet
    -0.26
    POSITIVE LOGITS
    éªļ
    0.27
    人éĻħ
    0.25
    åĨħå¤ĸ
    0.24
    æIJĶ
    0.24
    æĭĽçĶŁ
    0.23
    梢
    0.23
    ä¸Ģå¹ħ
    0.23
    ç¿ĺ
    0.23
     Planner
    0.23
    ieux
    0.23
    Activations Density 1.003%

    No Known Activations