© 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. 23-TRANSCODER-HP
    7. 25463
    Prev
    Next
    INDEX
    Explanations

    conditions and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    gorithm
    -0.27
    straints
    -0.26
    驹
    -0.25
    ETHOD
    -0.25
    ķĮ
    -0.24
    èĩ¾
    -0.23
    æ¯Ķè¾ĥç®Ģåįķ
    -0.23
    AndView
    -0.23
    rette
    -0.23
    ished
    -0.23
    POSITIVE LOGITS
    çĶļèĩ³
    1.99
    çĶļèĩ³æĺ¯
    1.69
     even
    1.61
    ä¹ĥèĩ³
    1.45
    even
    1.33
    çĶļèĩ³è¿ĺ
    1.32
     sogar
    1.20
     Even
    1.20
    Even
    1.16
     tháºŃm
    1.15
    Activations Density 0.014%

    No Known Activations