© 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. 130136
    Prev
    Next
    INDEX
    Explanations

    laws and policies

    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
    ijľ
    -0.29
    æľ¬æĸĩ
    -0.28
    cl
    -0.28
    å°±
    -0.28
    hal
    -0.27
    oud
    -0.27
    è¿Ļç¯ĩæĸĩç«ł
    -0.27
    Anyone
    -0.26
     ign
    -0.26
    asy
    -0.26
    POSITIVE LOGITS
    æ²ĸ
    0.29
    erate
    0.26
    å½ĵä¹ĭ
    0.26
    elter
    0.26
    ÑģÑĤÑĥп
    0.25
    èµī
    0.24
    ç»Į
    0.24
    EXIST
    0.24
    _Des
    0.24
    apol
    0.24
    Activations Density 11.155%

    No Known Activations