© 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. 25-TRANSCODER-HP
    7. 107285
    Prev
    Next
    INDEX
    Explanations

    population

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AQ
    -0.28
     exploit
    -0.27
    è¿Ļåľº
    -0.27
    åĪ¸
    -0.25
    夫
    -0.25
    è£ħè½½
    -0.24
     Whoever
    -0.24
    åĿļåĽº
    -0.24
    owntown
    -0.24
    adero
    -0.24
    POSITIVE LOGITS
     population
    0.44
     endangered
    0.39
    éĩİçĶŁåĬ¨çī©
    0.37
    éĩİçĶŁ
    0.36
     populations
    0.36
    angered
    0.36
     Population
    0.34
     birds
    0.34
    Population
    0.33
    population
    0.33
    Activations Density 0.920%

    No Known Activations