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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24775
    Prev
    Next
    INDEX
    Explanations

    0

    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
    çļĦ好
    -0.26
    建
    -0.26
    æĦ¿æľĽ
    -0.25
    ç©Ĩ
    -0.24
     Mills
    -0.24
     ba
    -0.24
     aba
    -0.23
    æªĶ
    -0.23
     later
    -0.23
    约
    -0.23
    POSITIVE LOGITS
    tone
    0.26
     Proud
    0.26
    deriv
    0.26
    GetWidth
    0.24
     décid
    0.24
    -INF
    0.24
    çĸijéĹ®
    0.24
    ffffff
    0.23
     оказ
    0.23
     beyond
    0.23
    Activations Density 0.047%

    No Known Activations