© 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. 95384
    Prev
    Next
    INDEX
    Explanations

    to

    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
    æŀģ
    -0.31
    -publish
    -0.28
    æĻ¯
    -0.28
    åıĺå¼Ĥ
    -0.28
    æŀ«
    -0.27
    ghost
    -0.26
    wp
    -0.26
    èIJİ缩
    -0.26
     bury
    -0.26
    çķ¹
    -0.26
    POSITIVE LOGITS
     truly
    0.48
     really
    0.43
    羣æŃ£
    0.40
     REALLY
    0.40
    羣æŃ£åģļåĪ°
    0.40
     realmente
    0.39
     Really
    0.39
    really
    0.39
    羣æŃ£çļĦ
    0.38
     adequately
    0.37
    Activations Density 0.892%

    No Known Activations