© 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. 53072
    Prev
    Next
    INDEX
    Explanations

    had

    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
     present
    -0.27
     Present
    -0.24
    uria
    -0.24
    .ToBoolean
    -0.24
    .toCharArray
    -0.24
    agos
    -0.23
    ãģĮãĤī
    -0.23
    -present
    -0.23
    itos
    -0.23
    imore
    -0.23
    POSITIVE LOGITS
     set
    0.30
    æıIJéĢŁ
    0.29
     carried
    0.28
     Const
    0.27
     presumed
    0.26
    ^K
    0.26
    çŃIJ
    0.26
    Fixed
    0.25
    æ³ķå®ļ
    0.24
    åĪĨå·¥
    0.24
    Activations Density 0.056%

    No Known Activations