© 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. 32-TRANSCODER-HP
    7. 41744
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩijèŀįåį±æľº
    -0.27
    ç²®
    -0.27
    åīįåı°
    -0.25
    è°¬
    -0.25
     positively
    -0.24
     GmbH
    -0.24
    éĩľ
    -0.24
     Banks
    -0.23
    positive
    -0.23
     pure
    -0.23
    POSITIVE LOGITS
    enci
    0.28
    suite
    0.28
    eria
    0.28
    abella
    0.26
    åŁŁ
    0.25
    ena
    0.25
    erÃŃa
    0.25
    adelphia
    0.24
    ched
    0.24
    camp
    0.24
    Activations Density 0.018%

    No Known Activations