© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161792
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ¥
    -0.27
    anders
    -0.27
     Abr
    -0.26
    é£Łåĵģ
    -0.25
     outdoors
    -0.24
    延éķ¿
    -0.24
    ä½ľæ¡Ī
    -0.24
    à¹Į
    -0.24
     unregister
    -0.24
    firm
    -0.23
    POSITIVE LOGITS
    igne
    0.27
     deductible
    0.26
     special
    0.26
     logical
    0.26
    utable
    0.26
    æĥħåĨµè¿Ľè¡Į
    0.25
     reflecting
    0.25
    ci
    0.25
     defined
    0.25
    pend
    0.25
    Activations Density 0.003%

    No Known Activations