© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25554
    Prev
    Next
    INDEX
    Explanations

    Generic text snippets

    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
    Negative Logits
    ldr
    -0.28
     ctor
    -0.26
     offer
    -0.26
    æĤĿ
    -0.25
    æıIJä¾Ľ
    -0.25
     anniversary
    -0.25
    ãĤ¢ãĥ³
    -0.25
     offering
    -0.25
    uffs
    -0.24
    egra
    -0.24
    POSITIVE LOGITS
    çģµæ´»æĢ§
    0.33
    åĬĽéĩı
    0.32
    å¸ĮæľĽ
    0.31
    ç¬ij声
    0.30
     expertise
    0.30
     flexibility
    0.30
     hope
    0.29
    ','#
    0.29
     guidance
    0.29
    温æļĸ
    0.29
    Activations Density 0.011%

    No Known Activations