© 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. 53623
    Prev
    Next
    INDEX
    Explanations

    Russian names

    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
    eselect
    -0.25
    èĶĵ
    -0.24
    éĥ¨
    -0.24
    bring
    -0.24
    [first
    -0.24
    èIJ¥
    -0.24
    Toolkit
    -0.23
     EÄŁitim
    -0.23
     spices
    -0.23
     Alg
    -0.23
    POSITIVE LOGITS
    ong
    0.32
    ften
    0.29
    äºĨä¸Ģ份
    0.29
    TY
    0.27
    /ion
    0.27
    èĩ
    0.27
    raq
    0.27
    TING
    0.26
    stre
    0.26
    继
    0.26
    Activations Density 0.794%

    No Known Activations