© 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. 95487
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     cont
    -0.40
     acc
    -0.35
     con
    -0.35
     com
    -0.35
     col
    -0.35
     cub
    -0.35
     conf
    -0.34
     conc
    -0.34
     comp
    -0.33
     dec
    -0.32
    POSITIVE LOGITS
    ãĢĤ↵↵↵↵↵↵
    0.26
    éĺ²çĽĹ
    0.26
    æݨèĸ¦
    0.26
    æĬĬ她
    0.26
    ä¸Ģæ³¢
    0.25
    andom
    0.25
    请çĤ¹åĩ»
    0.25
    ä¸Ģç§Ĵ
    0.25
    家åĸ»
    0.25
     NONINFRINGEMENT
    0.25
    Activations Density 0.966%

    No Known Activations