© 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. 42308
    Prev
    Next
    INDEX
    Explanations

    Industrial and computer concepts

    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
     Generate
    -0.35
    gener
    -0.35
     generate
    -0.33
     gener
    -0.33
     generated
    -0.31
     Generating
    -0.30
     generation
    -0.30
    .gener
    -0.30
    GENER
    -0.30
     generating
    -0.30
    POSITIVE LOGITS
    æ£ł
    0.28
    DidLoad
    0.26
    di
    0.26
     sak
    0.26
     isolated
    0.26
    ba
    0.25
    _di
    0.25
    æĶ¾åѦ
    0.25
    åĤįæĻļ
    0.25
    bam
    0.24
    Activations Density 0.000%

    No Known Activations