© 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. 107824
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
     easier
    -0.27
     low
    -0.26
     abused
    -0.26
     medium
    -0.26
    ä¼Ĺ
    -0.25
     medio
    -0.25
     easy
    -0.25
    çī©
    -0.25
    __;
    -0.24
    abus
    -0.24
    POSITIVE LOGITS
    æĥĬåĸľ
    0.27
    åł±å°İ
    0.27
    çī¹ç§į
    0.26
     Ful
    0.26
    Unc
    0.26
    æĪijå¿ĥéĩĮ
    0.25
    ä¿Ŀ驾
    0.25
    spot
    0.24
    edef
    0.24
    .asp
    0.24
    Activations Density 2.220%

    No Known Activations