© 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. 33-TRANSCODER-HP
    7. 53613
    Prev
    Next
    INDEX
    Explanations

    prefix "dis"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inium
    -0.29
    EDIA
    -0.28
    ICATION
    -0.27
     defaulted
    -0.27
    anst
    -0.27
    æ¯ıä¸Ģ天
    -0.26
    dings
    -0.25
     Defaults
    -0.25
    uraa
    -0.25
    -san
    -0.25
    POSITIVE LOGITS
    im
    0.33
    mod
    0.28
    b
    0.28
    cc
    0.27
    ment
    0.27
     bore
    0.27
    å¼ŁåŃIJ
    0.27
    bro
    0.27
    leg
    0.26
    æİĴåĪĹ
    0.26
    Activations Density 0.012%

    No Known Activations