© 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. 162846
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     lat
    -0.27
    agged
    -0.26
    DetailView
    -0.26
    åī¥å¤º
    -0.25
     ÑĤеле
    -0.24
    æĪIJéķ¿
    -0.24
     Contest
    -0.24
    åħ¬æŃ£
    -0.23
     Joh
    -0.23
    çĿĽ
    -0.23
    POSITIVE LOGITS
    wald
    0.32
    ละ
    0.28
     regulated
    0.27
    æ°´éĩı
    0.26
     básico
    0.26
    LOW
    0.25
    plaintext
    0.25
     prospect
    0.25
    ewood
    0.25
    è²»
    0.25
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.