© 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. 162743
    Prev
    Next
    INDEX
    Explanations

    months

    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
    à¦Ł
    -0.25
    auty
    -0.24
     Cater
    -0.24
     днÑı
    -0.24
    çģµæķı
    -0.24
    ISIBLE
    -0.23
     simplify
    -0.23
    缮ãģ«
    -0.23
    ascal
    -0.23
    è¿IJè¾ĵ
    -0.23
    POSITIVE LOGITS
    hart
    0.31
     scatter
    0.27
     gra
    0.26
    _CE
    0.25
     Grat
    0.25
     samp
    0.24
    iche
    0.24
    å°±è¶Ĭ
    0.24
     пÑĢек
    0.24
    hf
    0.23
    Activations Density 0.037%

    No Known Activations