© 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. 162946
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    åľ¨å®¶éĩĮ
    -0.31
    åľ¨å®¶
    -0.30
    å®Įæķ´çļĦ
    -0.28
    ä¸įæĪIJ
    -0.28
     them
    -0.28
    èĮ¸
    -0.26
     peÅĤ
    -0.26
    æľ¬èº«
    -0.26
    æľ¬èº«çļĦ
    -0.26
    fee
    -0.25
    POSITIVE LOGITS
    Pont
    0.27
    _except
    0.26
    .generated
    0.26
     Tribune
    0.26
     despite
    0.26
    æłī
    0.26
    coli
    0.25
     spirits
    0.25
     incumb
    0.25
    èļĿ
    0.24
    Activations Density 0.001%

    No Known Activations