© 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. 20-TRANSCODER-HP
    7. 129667
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presumably
    -0.42
     whatever
    -0.33
     somehow
    -0.31
    umably
    -0.31
     possibly
    -0.31
    æĺ¯ä»Ģä¹Īåij¢
    -0.30
     perhaps
    -0.29
    æĥ³å¿ħ
    -0.28
     likely
    -0.27
     Surely
    -0.27
    POSITIVE LOGITS
    æĪijè¿ĺæĺ¯
    0.28
    ksi
    0.27
    åĨ³
    0.26
    called
    0.26
     loan
    0.25
    alic
    0.25
    icap
    0.25
    rama
    0.24
    emi
    0.24
     ISA
    0.24
    Activations Density 6.411%

    No Known Activations