© 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. 141030
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and names

    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
    cope
    -0.26
    /google
    -0.25
    grown
    -0.25
    å¯Ĵ
    -0.25
     Haz
    -0.24
    aneously
    -0.24
     familiar
    -0.23
    uali
    -0.23
     scratch
    -0.23
    èĭį
    -0.23
    POSITIVE LOGITS
    åªĴä½ĵæĬ¥éģĵ
    0.26
    _mB
    0.24
    ıntı
    0.23
    è·ij
    0.23
    æĭ¦æĪª
    0.23
     merit
    0.23
    ç¥Ģ
    0.23
     vog
    0.23
    agra
    0.22
    çĶµåİĤ
    0.22
    Activations Density 50.302%

    No Known Activations