© 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. 161752
    Prev
    Next
    INDEX
    Explanations

    wrote/writes

    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
    boxing
    -0.28
    ampling
    -0.27
    çī¹æĿĥ
    -0.27
    (EXIT
    -0.27
     tra
    -0.26
    SEP
    -0.26
     sampling
    -0.25
     specialty
    -0.25
    ocity
    -0.24
     ourselves
    -0.24
    POSITIVE LOGITS
    ä¸ĭåĪĹ
    0.32
    :↵↵
    0.30
    :
    0.29
    以ä¸ĭæĺ¯
    0.27
    ä¸ĭéĿ¢æĺ¯
    0.27
    以ä¸ĭ
    0.26
    就说
    0.26
     brag
    0.26
    ä¸ĭéĿ¢
    0.26
    çĶŁæ¶¯
    0.25
    Activations Density 0.015%

    No Known Activations