© 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. 32-TRANSCODER-HP
    7. 40967
    Prev
    Next
    INDEX
    Explanations

    Sperm related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĹ©æĹ©
    -0.28
    orth
    -0.27
    =device
    -0.27
    为大家
    -0.27
    reta
    -0.27
    æľĢåħĪè¿ĽçļĦ
    -0.26
    çµ²
    -0.26
    executor
    -0.25
    ordo
    -0.25
    etry
    -0.25
    POSITIVE LOGITS
    AIL
    0.31
    票
    0.30
     mic
    0.29
    AKE
    0.28
    ati
    0.28
    å¾®
    0.27
    Mic
    0.27
    mic
    0.26
     cortical
    0.26
    odium
    0.26
    Activations Density 0.016%

    No Known Activations