© 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. 30-TRANSCODER-HP
    7. 96716
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     orig
    -0.31
    ä¸Ģ对
    -0.29
    orig
    -0.28
     origin
    -0.27
    .origin
    -0.27
    agas
    -0.27
    aken
    -0.26
    Gas
    -0.26
    pecies
    -0.26
     Orig
    -0.26
    POSITIVE LOGITS
     recomm
    0.27
     butcher
    0.26
     FontAwesome
    0.25
    æݨèįIJ
    0.25
    ert
    0.25
    templ
    0.25
    iamond
    0.25
    core
    0.25
    terior
    0.25
    bbing
    0.25
    Activations Density 0.099%

    No Known Activations