© 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. 43106
    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_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
    å°½
    -0.34
    xE
    -0.28
    indre
    -0.27
    çĽ¡
    -0.27
    qe
    -0.26
    trie
    -0.25
    cased
    -0.25
    ÑĨев
    -0.24
    çĽĸ
    -0.24
    tn
    -0.24
    POSITIVE LOGITS
    ç¥ľ
    0.27
     decay
    0.27
    usp
    0.26
    decay
    0.26
    erator
    0.26
    çĽħ
    0.26
    æīĭåĨĮ
    0.25
    çĶ³æĬ¥
    0.25
    ç»ĥ
    0.24
    é³Į
    0.24
    Activations Density 0.001%

    No Known Activations