© 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. 54135
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    nı
    -0.30
     neur
    -0.28
    æŶä¸į
    -0.27
    rá
    -0.25
    lige
    -0.25
    -da
    -0.24
     bodily
    -0.24
     neurop
    -0.24
    dash
    -0.24
     ÑĢа
    -0.24
    POSITIVE LOGITS
     Flag
    0.31
    entine
    0.31
    ife
    0.28
     mar
    0.27
    IFICATIONS
    0.27
     Evolution
    0.27
     Islam
    0.27
    clone
    0.27
     Evil
    0.26
     Football
    0.26
    Activations Density 0.007%

    No Known Activations