© 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. 162925
    Prev
    Next
    INDEX
    Explanations

    in

    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
     might
    -0.26
    ủng
    -0.25
    累累
    -0.25
     could
    -0.24
    溯æºIJ
    -0.24
    æĪªåĽ¾
    -0.24
     tip
    -0.24
     önünde
    -0.24
     accr
    -0.24
     toxicity
    -0.24
    POSITIVE LOGITS
    çļĦéĩįè¦ģæĢ§
    0.25
    æĿµ
    0.24
    .</
    0.24
     Bris
    0.24
     rush
    0.24
    _DSP
    0.23
    IMPORTANT
    0.23
    æīĢéľĢè¦ģçļĦ
    0.23
     пÑĢежде
    0.23
    éĤ£ä¹Īç®Ģåįķ
    0.23
    Activations Density 0.005%

    No Known Activations