© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8920
    Prev
    Next
    INDEX
    Explanations

    Childbirth and delivery

    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
    Not in Any Lists

    No Comments

    Negative Logits
     interviews
    -0.52
     interview
    -0.48
    访è°Ī
    -0.43
     Interviews
    -0.42
     visits
    -0.42
     Interview
    -0.41
    Interview
    -0.40
     interviewed
    -0.40
     interviewing
    -0.38
     visit
    -0.37
    POSITIVE LOGITS
    天èĬ±æĿ¿
    0.28
    çĶµåĻ¨
    0.26
     Asians
    0.26
     Ñģез
    0.26
    èĩªç§ģ
    0.25
     гÑĢ
    0.25
     discriminator
    0.24
    ÑĤал
    0.24
    eps
    0.24
    çĽijå¯Ł
    0.23
    Activations Density 0.006%

    No Known Activations