© 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. 30178
    Prev
    Next
    INDEX
    Explanations

    order

    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
    ihn
    -0.27
    rieve
    -0.24
    峡
    -0.24
    ivr
    -0.24
    bah
    -0.24
    anson
    -0.24
    ookie
    -0.24
    aceutical
    -0.24
    ptime
    -0.24
    wcs
    -0.24
    POSITIVE LOGITS
    иж
    0.25
    欧
    0.24
    渺
    0.24
     min
    0.24
     Contribution
    0.24
     herr
    0.23
    çļĦ积æŀģæĢ§
    0.23
     blinded
    0.23
     Daw
    0.23
    Con
    0.23
    Activations Density 3.806%

    No Known Activations