© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161673
    Prev
    Next
    INDEX
    Explanations

    Overview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    好äºĭ
    -0.24
    usement
    -0.24
    诲
    -0.24
    æĹ¥è®¯
    -0.24
    izont
    -0.24
    æ°ª
    -0.23
    为空
    -0.23
    levation
    -0.22
    monds
    -0.22
     gere
    -0.22
    POSITIVE LOGITS
     дол
    0.29
     coc
    0.24
    cup
    0.24
    ÑĢÑı
    0.24
    æ±Łä¸ľ
    0.24
    dü
    0.24
    饧
    0.23
    elves
    0.23
    artner
    0.23
     uplift
    0.23
    Activations Density 0.073%

    No Known Activations