© 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. 54111
    Prev
    Next
    INDEX
    Explanations

    study

    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
    å¾Ĺä½ı
    -0.29
    ationToken
    -0.29
    çį¾
    -0.27
    æ´Ĺ澡
    -0.26
     Imper
    -0.26
    ivor
    -0.26
    efined
    -0.25
    voir
    -0.25
    ifications
    -0.25
     impres
    -0.24
    POSITIVE LOGITS
     study
    0.34
     lengths
    0.32
    study
    0.32
     laws
    0.30
    =set
    0.30
     set
    0.29
    bones
    0.28
     Study
    0.28
    systems
    0.28
     one
    0.28
    Activations Density 0.038%

    No Known Activations