© 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. 23416
    Prev
    Next
    INDEX
    Explanations

    cref

    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
     nowhere
    -0.27
    TA
    -0.26
    etch
    -0.25
    åıĹåĪ°å½±åĵį
    -0.25
    inn
    -0.24
    åĬŀæ³ķ
    -0.24
     hole
    -0.23
    schlä
    -0.23
    çļĦåĬŀæ³ķ
    -0.23
    iness
    -0.23
    POSITIVE LOGITS
    vro
    0.28
    rdf
    0.27
     Lisp
    0.27
    oons
    0.26
     Force
    0.26
     Gerr
    0.25
    ruk
    0.25
    gorithm
    0.25
    nze
    0.25
     Forces
    0.25
    Activations Density 0.006%

    No Known Activations