© 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. 9-TRANSCODER-HP
    7. 29711
    Prev
    Next
    INDEX
    Explanations

    "so", consequential clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĪŀ
    -0.31
    ablish
    -0.30
    åijĽ
    -0.29
    ạn
    -0.28
    ä¿£
    -0.27
    æĪijä¸įçŁ¥éģĵ
    -0.26
    å®ĵ
    -0.26
    dance
    -0.26
     rape
    -0.26
     raped
    -0.25
    POSITIVE LOGITS
    .Reference
    0.28
    æ¢Ń
    0.25
     reference
    0.25
    umeric
    0.25
     ov
    0.25
     Covent
    0.24
    身ä½ĵ
    0.24
     sino
    0.24
    ãĤĤãģ®
    0.23
    elow
    0.23
    Activations Density 0.166%

    No Known Activations