© 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. 163165
    Prev
    Next
    INDEX
    Explanations

    Introducing a limitation/exception

    np_max-act · gemini-2.0-flash
    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
     perse
    -0.28
    ioned
    -0.27
    å¯IJ
    -0.27
    çħ
    -0.26
    åįĩéĻį
    -0.26
    Õ§
    -0.25
    æĵ¾
    -0.25
    mie
    -0.25
    æľĢ强
    -0.24
    allet
    -0.24
    POSITIVE LOGITS
    缺ä¹ı
    0.63
     lack
    0.61
     lacks
    0.52
    å¾Īå°ij
    0.49
     unknown
    0.47
    åĩłä¹İ没æľī
    0.47
    ä¸įæ¸ħæ¥ļ
    0.46
     lacked
    0.46
     lacking
    0.45
    æľªçŁ¥
    0.45
    Activations Density 0.062%

    No Known Activations