© 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. 27-TRANSCODER-HP
    7. 57713
    Prev
    Next
    INDEX
    Explanations

    technical/scientific excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·¥ç¨ĭæĬĢæľ¯
    -0.30
    rev
    -0.28
    ç«
    -0.27
    quo
    -0.26
    LEncoder
    -0.24
    ville
    -0.24
    人身
    -0.24
     Votes
    -0.24
    á»Į
    -0.23
    çĿĢä»ĸ
    -0.23
    POSITIVE LOGITS
    enson
    0.29
    åģ¶çĦ¶
    0.25
    æī§
    0.25
    /run
    0.24
    моÑĢ
    0.24
    èµĦ讯
    0.24
    cob
    0.24
     Tested
    0.24
    带åĪ°
    0.23
     hac
    0.23
    Activations Density 0.010%

    No Known Activations