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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162659
    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
    oftware
    -0.35
    èĴĻ
    -0.26
    åľº
    -0.26
    ikon
    -0.26
    ARK
    -0.26
    ark
    -0.25
    acula
    -0.25
    Tier
    -0.25
    anax
    -0.24
    å¤į
    -0.24
    POSITIVE LOGITS
    æĢ§åĴĮ
    0.28
     rele
    0.26
    itive
    0.25
    åŁ¹åħ»åѦçĶŁ
    0.25
    çŁ¥åIJįä¼ģä¸ļ
    0.25
    å«Į
    0.25
     ÑĨел
    0.25
    å®ŀåľ¨
    0.24
     baiser
    0.24
    æĢ§
    0.24
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.