© 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. 64319
    Prev
    Next
    INDEX
    Explanations

    each

    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
    ace
    -0.28
    Anth
    -0.28
    çݺ
    -0.27
     Anth
    -0.25
    ContextHolder
    -0.24
    áĢĦ
    -0.24
    .prepareStatement
    -0.24
    _ABC
    -0.24
    åIJĦçľģ
    -0.24
     coat
    -0.24
    POSITIVE LOGITS
    æł¸å®ļ
    0.32
    çļĦæ¦Ĥ念
    0.30
    çļĦè´¨éĩı
    0.29
     hypo
    0.29
    Ļ¶
    0.28
    çī¹çĤ¹æĺ¯
    0.28
    å°±çŁ¥éģĵ
    0.27
    æ¦Ĥ念
    0.26
     major
    0.25
    óln
    0.25
    Activations Density 13.840%

    No Known Activations