© 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. 161973
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    dff
    -0.29
     interpolated
    -0.26
    otr
    -0.25
    åı£å¤´
    -0.25
    dns
    -0.25
     facing
    -0.25
    .ObjectModel
    -0.25
     mare
    -0.24
     anus
    -0.24
    符
    -0.24
    POSITIVE LOGITS
    请éĹ®
    0.36
    âĢ¦”
    0.32
     __________________
    0.32
    åķı
    0.32
    请éĢīæĭ©
    0.31
    âĢ¦↵↵↵↵
    0.31
    âĢ¦"
    0.31
     ______
    0.30
    ________
    0.30
    oran
    0.30
    Activations Density 0.070%

    No Known Activations