© 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. 63431
    Prev
    Next
    INDEX
    Explanations

    superlative

    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
    PCS
    -0.28
    Scripts
    -0.27
     Scripts
    -0.27
     Levy
    -0.26
    ä¹ĭ家
    -0.26
    åĻİ
    -0.25
     Gund
    -0.25
     dug
    -0.25
    æĥ³
    -0.24
    æĥ³çĿĢ
    -0.24
    POSITIVE LOGITS
    è°ĥéħį
    0.25
    èĺħ
    0.25
    /gr
    0.25
    reste
    0.24
    gr
    0.24
    gregation
    0.24
     HARD
    0.24
     limited
    0.24
    ýt
    0.24
    è°ħ解
    0.24
    Activations Density 4.033%

    No Known Activations