© 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. 32-TRANSCODER-HP
    7. 43291
    Prev
    Next
    INDEX
    Explanations

    Childbirth context

    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
    Not in Any Lists

    No Comments

    Negative Logits
     labor
    -0.33
    åĬ³åĬ¨
    -0.31
     deliver
    -0.30
     contr
    -0.30
     delivery
    -0.30
    交ä»ĺ
    -0.30
    onian
    -0.29
     labour
    -0.28
    管çIJĨä¸Ńå¿ĥ
    -0.28
    Smarty
    -0.27
    POSITIVE LOGITS
    PASS
    0.27
    steller
    0.26
    rial
    0.25
    èĤ¾
    0.24
    .imp
    0.24
    rib
    0.23
    adir
    0.23
     spontaneous
    0.23
    .pass
    0.23
    phony
    0.23
    Activations Density 0.007%

    No Known Activations