© 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. 30-TRANSCODER-HP
    7. 96285
    Prev
    Next
    INDEX
    Explanations

    light

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     craftsmanship
    -0.30
    Craft
    -0.28
     Craft
    -0.27
    æ¼Ĩ
    -0.27
    æĮ¤
    -0.26
    maj
    -0.26
    éĴ»çłĶ
    -0.26
    åĪł
    -0.25
     обÑıз
    -0.25
     Mont
    -0.25
    POSITIVE LOGITS
     falling
    0.56
    èIJ½
    0.55
     fallen
    0.52
    èIJ½åĪ°
    0.49
     falls
    0.47
    èIJ½åľ¨
    0.46
     fall
    0.45
    fall
    0.45
    èIJ½ä¸ĭ
    0.44
    èIJ½åħ¥
    0.42
    Activations Density 0.889%

    No Known Activations