© 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. 88432
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èİ«è¿ĩäºİ
    -0.27
    污æŁĵçī©
    -0.25
    代è¨Ģ
    -0.25
    -panel
    -0.25
    isy
    -0.24
    è®Ń
    -0.24
    ä½łå°±
    -0.24
    æĩ
    -0.24
    ollo
    -0.24
    reon
    -0.24
    POSITIVE LOGITS
     flag
    0.27
    éĢļãĤĬ
    0.26
    flag
    0.25
    被åĬ¨
    0.25
    ĪæĿĥ
    0.24
    .flag
    0.24
    (flag
    0.24
    éħįæĸĻ
    0.24
    硬
    0.24
    çĥ§çĥ¤
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.