© 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. 25322
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     wyglÄħda
    -0.26
     Jared
    -0.26
    æĹ©
    -0.25
     Assad
    -0.25
    anter
    -0.25
    çī¹æ´¾åijĺ
    -0.24
    early
    -0.24
    iability
    -0.23
    audi
    -0.23
    otch
    -0.23
    POSITIVE LOGITS
    çois
    0.29
    åıĪèĥ½
    0.26
     Pl
    0.26
    æ§İ
    0.26
    thane
    0.25
     dif
    0.25
     plur
    0.24
    çīĪæĿĥå½ĴåİŁ
    0.24
     Pref
    0.24
    afone
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.