© 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. 24-TRANSCODER-HP
    7. 149461
    Prev
    Next
    INDEX
    Explanations

    trauma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.28
    nya
    -0.27
    ings
    -0.27
    ernal
    -0.25
     Held
    -0.25
    pany
    -0.25
    shire
    -0.25
    sel
    -0.24
    ìľ¼
    -0.24
    ritel
    -0.24
    POSITIVE LOGITS
    learning
    0.26
    çļĦåŃ¦ä¹ł
    0.25
    esch
    0.25
    ën
    0.24
    vere
    0.24
    xBC
    0.24
    anst
    0.23
     caÅĤego
    0.23
    侧
    0.23
    fixtures
    0.23
    Activations Density 1.528%

    No Known Activations