© 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. 22-TRANSCODER-HP
    7. 87779
    Prev
    Next
    INDEX
    Explanations

    Skepticism/atheism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ijäºĽ
    -0.25
     segurança
    -0.24
    tail
    -0.24
    po
    -0.23
    regular
    -0.23
    grab
    -0.23
    angi
    -0.23
    gh
    -0.23
    æĬ¢åĬ«
    -0.23
     Bei
    -0.22
    POSITIVE LOGITS
    arguments
    0.27
     truths
    0.26
    IALOG
    0.25
     depreci
    0.25
    .statistics
    0.24
     finding
    0.24
    reon
    0.24
    æĸ¯çī¹
    0.24
    -minded
    0.23
    eres
    0.23
    Activations Density 0.028%

    No Known Activations