© 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. 27-TRANSCODER-HP
    7. 58504
    Prev
    Next
    INDEX
    Explanations

    sleep and/or erections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    language
    -0.27
    łģ
    -0.27
    对å¤ĸ
    -0.26
     пÑĢава
    -0.26
    æ°Ķè´¨
    -0.26
    央
    -0.25
     language
    -0.25
    myModal
    -0.25
    海岸
    -0.24
    ico
    -0.23
    POSITIVE LOGITS
    pes
    0.28
     quick
    0.26
    .ur
    0.25
    DMI
    0.24
     vine
    0.24
    ONUS
    0.24
    pel
    0.24
    StartElement
    0.24
    Quick
    0.24
    start
    0.24
    Activations Density 0.008%

    No Known Activations