© 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. 14-TRANSCODER-HP
    7. 41686
    Prev
    Next
    INDEX
    Explanations

    Code, citations, legal jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    лаÑĤ
    -0.27
    åľ°çIJĨ
    -0.26
    ]'
    -0.25
    odzi
    -0.24
    åĪĹ
    -0.23
    indi
    -0.23
    ady
    -0.23
    æ´½
    -0.23
    å·Ŀ
    -0.23
    ë¦ĩ
    -0.23
    POSITIVE LOGITS
    utter
    0.27
    moid
    0.26
     (~(
    0.25
    comb
    0.24
    -Saharan
    0.24
    antis
    0.24
     premises
    0.24
     reinforcements
    0.23
     pau
    0.23
    ä¸ĢæĿ¯
    0.23
    Activations Density 0.739%

    No Known Activations