© 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. 163108
    Prev
    Next
    INDEX
    Explanations

    sheet

    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
     nip
    -0.26
    ypress
    -0.26
    ç¥Ŀ
    -0.25
    ason
    -0.25
    orts
    -0.25
     Commit
    -0.25
    æĿł
    -0.24
    æłĩå¿Ĺ
    -0.24
    è´·
    -0.24
    ittest
    -0.24
    POSITIVE LOGITS
     attached
    0.28
    缤
    0.28
     enclosed
    0.27
    çĽĺ
    0.27
    åĨĽ
    0.27
    attached
    0.27
     attachment
    0.25
     appended
    0.25
    _argv
    0.24
    /disc
    0.24
    Activations Density 0.010%

    No Known Activations