© 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. 53736
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and titles

    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
     gratuita
    -0.26
    ải
    -0.25
     grátis
    -0.24
    éĤ£
    -0.24
    .ga
    -0.23
    æĢ»ä½ĵ
    -0.23
     hogy
    -0.23
    ä¸Ńæľī
    -0.23
    该
    -0.23
    绣ä¸Ģ
    -0.23
    POSITIVE LOGITS
     IV
    0.41
     III
    0.39
     IX
    0.36
     VIII
    0.35
     II
    0.35
     VII
    0.33
     jr
    0.33
     VI
    0.33
     Sr
    0.32
     Jr
    0.31
    Activations Density 0.234%

    No Known Activations