© 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. 53093
    Prev
    Next
    INDEX
    Explanations

    Technical or unusual content

    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
    红
    -0.41
     red
    -0.40
    red
    -0.33
    -red
    -0.32
     blue
    -0.32
    ç´ħ
    -0.32
    èĵĿ
    -0.32
    Red
    -0.30
    _red
    -0.30
     Red
    -0.30
    POSITIVE LOGITS
    /kernel
    0.30
    KERNEL
    0.26
    ü
    0.25
    æ©¡
    0.25
    /Branch
    0.24
    collapse
    0.23
    ï¼µ
    0.23
     collapsed
    0.23
    ä¸įçŁ¥éģĵ
    0.23
    usr
    0.23
    Activations Density 0.229%

    No Known Activations