© 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. 32-TRANSCODER-HP
    7. 41183
    Prev
    Next
    INDEX
    Explanations

    studies with participants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirty
    -0.35
     patient
    -0.33
     ninety
    -0.31
     Patient
    -0.30
     fifty
    -0.30
     fifteen
    -0.29
     sixty
    -0.29
     seventy
    -0.29
    ä¹Ŀåįģ
    -0.29
     customer
    -0.29
    POSITIVE LOGITS
    ayo
    0.27
    fg
    0.26
    Logic
    0.26
    зи
    0.26
     interns
    0.25
    çĽĴ
    0.25
    æľīåħ´è¶£
    0.24
     volunteers
    0.24
     supervisors
    0.24
    硬
    0.24
    Activations Density 0.048%

    No Known Activations