© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42520
    Prev
    Next
    INDEX
    Explanations

    fact checking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çłĶ究
    -0.52
     research
    -0.49
    research
    -0.47
    çłĶ
    -0.44
    çłĶ究人åijĺ
    -0.42
    Research
    -0.42
     Research
    -0.40
     researchers
    -0.40
    çļĦçłĶ究
    -0.40
     researcher
    -0.39
    POSITIVE LOGITS
     fact
    0.30
    endir
    0.28
    çļĦäºĭå®ŀ
    0.26
    è´Łæĭħ
    0.26
    pton
    0.26
    FACT
    0.26
     check
    0.25
    checks
    0.25
    缴
    0.25
    å¯Įæ°ij
    0.25
    Activations Density 0.006%

    No Known Activations