© 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. 53234
    Prev
    Next
    INDEX
    Explanations

    Cyrillic languages

    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
     коÑĤоÑĢÑĭм
    -0.56
     ÑįÑĤим
    -0.47
     którym
    -0.45
    ÑİÑīим
    -0.44
    ÑĪим
    -0.44
    еннÑĭм
    -0.44
    овÑĭм
    -0.44
     ÑĤаким
    -0.43
    нÑĭм
    -0.43
     tym
    -0.42
    POSITIVE LOGITS
     коÑĤоÑĢ
    0.48
     MU
    0.31
    иÑĢÑĥÑİÑī
    0.30
    mu
    0.30
    MU
    0.29
     mu
    0.28
    нÑİ
    0.28
     деÑĤÑģк
    0.28
     амеÑĢиканÑģк
    0.28
    ishop
    0.27
    Activations Density 0.123%

    No Known Activations