© 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. 24-TRANSCODER-HP
    7. 149677
    Prev
    Next
    INDEX
    Explanations

    Code and internet addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cente
    -0.26
    éħįæĸ¹
    -0.25
    enums
    -0.25
    å®īå®ļ
    -0.25
    çļĦ人çĶŁ
    -0.24
    license
    -0.24
    beg
    -0.24
    choice
    -0.24
    满äºĨ
    -0.24
    baseline
    -0.23
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.33
    è¿ĻäºĽéĹ®é¢ĺ
    0.32
    ä½Ĩæĺ¯åľ¨
    0.31
    çĦ¶èĢĮ
    0.30
     However
    0.29
    ä½Ĩåľ¨
    0.29
    çķ¢ç«Ł
    0.29
    èĢĮåľ¨
    0.28
     però
    0.28
     Luckily
    0.27
    Activations Density 0.299%

    No Known Activations