© 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. 20-TRANSCODER-HP
    7. 129769
    Prev
    Next
    INDEX
    Explanations

    central

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    สว
    -0.29
    stud
    -0.29
    irit
    -0.27
     Ens
    -0.25
     Weeks
    -0.25
    ä»Ģä¹Īäºĭ
    -0.25
    çĸĹç¨ĭ
    -0.25
     W
    -0.24
    WT
    -0.23
    缸åºĶçļĦ
    -0.23
    POSITIVE LOGITS
    ices
    0.29
    ×ķ׾×Ŀ
    0.28
    ict
    0.28
    ÑģÑħ
    0.27
    iced
    0.26
    vê
    0.26
    åĢĻéĢī人
    0.24
    icing
    0.24
    veal
    0.24
    ä¹Łæĺ¯ä¸Ģ个
    0.24
    Activations Density 14.592%

    No Known Activations