© 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. 54052
    Prev
    Next
    INDEX
    Explanations

    Instructions and descriptions

    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
    çĽĴåŃIJ
    -0.30
     table
    -0.29
    boxes
    -0.28
    Boxes
    -0.28
     boxes
    -0.27
     basin
    -0.27
    box
    -0.27
     hed
    -0.26
     martin
    -0.26
     Basin
    -0.25
    POSITIVE LOGITS
    å°½åĬĽ
    0.28
    ernal
    0.26
    avour
    0.25
    åIJĥ
    0.25
    ħ§
    0.25
    åºŁ
    0.25
    åŃĺ
    0.25
    æĹĹ
    0.25
    åŃļ
    0.25
    /memory
    0.24
    Activations Density 0.008%

    No Known Activations