© 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. 53285
    Prev
    Next
    INDEX
    Explanations

    the

    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
    è§Ħå¾ĭ
    -0.28
    ansa
    -0.27
    åĽ¾çīĩæĿ¥æºIJ
    -0.25
    åĶ®
    -0.25
    asan
    -0.25
    ä¸Ģ头
    -0.25
    è§ĦåĪĻ
    -0.25
    alte
    -0.24
    elix
    -0.24
    .rules
    -0.24
    POSITIVE LOGITS
     chart
    0.26
    :].
    0.26
     heap
    0.25
     denote
    0.25
     hexadecimal
    0.25
     prime
    0.25
     report
    0.25
     scatter
    0.24
     tet
    0.24
     pie
    0.23
    Activations Density 0.030%

    No Known Activations