© 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. 23724
    Prev
    Next
    INDEX
    Explanations

    Prepositions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ounce
    -0.28
    alcon
    -0.26
    å°ijäºĨ
    -0.25
    åī©ä¸ĭ
    -0.25
    ata
    -0.25
    ake
    -0.25
    -alone
    -0.24
    akin
    -0.24
    arial
    -0.24
    cluded
    -0.24
    POSITIVE LOGITS
    åı¦ä¸Ģä½į
    0.29
    åĪĽå§ĭ人
    0.25
     margins
    0.25
    ÑĮÑı
    0.25
     Marg
    0.25
    William
    0.24
     Dra
    0.24
    ç®´
    0.24
    Marg
    0.24
     JsonConvert
    0.24
    Activations Density 0.027%

    No Known Activations