© 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. 24503
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     calculate
    -0.33
    Coefficient
    -0.32
     multiplier
    -0.32
     magnitude
    -0.31
    计ç®Ĺ
    -0.31
     calculating
    -0.31
     calculates
    -0.31
     quantify
    -0.31
    åĥ¹åĢ¼
    -0.31
     coefficient
    -0.30
    POSITIVE LOGITS
     motion
    0.28
    âĬĩ
    0.28
    ç©¿
    0.26
     positioning
    0.26
     RANGE
    0.26
    motion
    0.25
    丰å¯ĮçļĦ
    0.25
    æł·
    0.24
     unloaded
    0.24
    OfString
    0.24
    Activations Density 0.001%

    No Known Activations