© 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. 9-TRANSCODER-HP
    7. 30180
    Prev
    Next
    INDEX
    Explanations

    adaptive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    稿
    -0.28
     enumerated
    -0.27
    æ·±åİļçļĦ
    -0.27
    owie
    -0.26
    onden
    -0.25
     partido
    -0.25
    agar
    -0.25
    ours
    -0.25
    顽强
    -0.24
    ãĥŃãĥ¼
    -0.24
    POSITIVE LOGITS
     consistency
    0.28
     recon
    0.26
    èij¡
    0.26
     volta
    0.25
    éĤ¾
    0.25
    Optional
    0.25
     Marr
    0.24
     backed
    0.24
     Consumer
    0.24
     Photograph
    0.24
    Activations Density 1.519%

    No Known Activations