© 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. 18-TRANSCODER-HP
    7. 88401
    Prev
    Next
    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įä¼ļ
    -0.28
    åijĬ
    -0.28
    lap
    -0.28
    å®ŀå®ŀåľ¨åľ¨
    -0.26
    itol
    -0.25
     gras
    -0.25
    haled
    -0.25
     converged
    -0.24
    (Void
    -0.24
     theirs
    -0.24
    POSITIVE LOGITS
    è´¶
    0.28
    è´¨éĩıåĴĮ
    0.26
    EDITOR
    0.26
    审
    0.25
    ahi
    0.25
    ilm
    0.24
    åī§åľº
    0.24
    æľºä½ĵ
    0.24
     classifiers
    0.24
    åħļåĴĮ
    0.24
    Activations Density 7.094%

    No Known Activations