© 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. 33-TRANSCODER-HP
    7. 53869
    Prev
    Next
    INDEX
    Explanations

    C

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    渣
    -0.28
    åĪ®
    -0.27
    åįİ
    -0.27
    uele
    -0.26
    sci
    -0.26
    éĶģ
    -0.26
    å¼Ģ设
    -0.25
     speaking
    -0.25
    ç»Ĩ
    -0.25
    avras
    -0.24
    POSITIVE LOGITS
    çļĦåį°è±¡
    0.29
    -pay
    0.27
    NOP
    0.27
    æľķ
    0.26
    çļĦ积æŀģæĢ§
    0.24
    erves
    0.24
    å¾Ĺä½ı
    0.24
    被æ·ĺæ±°
    0.24
    .axes
    0.23
    产ä¸ļåĽŃåĮº
    0.23
    Activations Density 0.017%

    No Known Activations