© 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. 52923
    Prev
    Next
    INDEX
    Explanations

    quantum physics

    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
     назад
    -0.27
    åŃº
    -0.27
    gef
    -0.26
    arer
    -0.25
    =cut
    -0.25
    redd
    -0.25
    ngo
    -0.25
    åģı
    -0.25
    institution
    -0.25
     наÑĤÑĥÑĢалÑĮн
    -0.25
    POSITIVE LOGITS
     pul
    0.34
    æĹłæīĢ
    0.33
    astic
    0.30
     cal
    0.28
     elementary
    0.28
     ped
    0.27
    azzo
    0.27
     condensed
    0.27
     ping
    0.27
     val
    0.27
    Activations Density 0.067%

    No Known Activations