© 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. 163205
    Prev
    Next
    INDEX
    Explanations

    Steve

    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
    onal
    -0.30
    chts
    -0.26
    onnement
    -0.26
    ennai
    -0.25
    ilter
    -0.25
    mond
    -0.24
    acement
    -0.24
    rame
    -0.24
    ansk
    -0.24
    mitted
    -0.23
    POSITIVE LOGITS
     predecessor
    0.24
     termin
    0.24
    åħ¨æĸĩ
    0.24
     Heck
    0.23
    iations
    0.23
    	View
    0.23
     Ireland
    0.23
     preceded
    0.22
     FIX
    0.22
     consistently
    0.22
    Activations Density 0.355%

    No Known Activations