© 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. 53488
    Prev
    Next
    INDEX
    Explanations

    lasers and optics

    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
    cou
    -0.28
     optical
    -0.28
     cap
    -0.26
     élect
    -0.25
     nose
    -0.25
     cou
    -0.25
    OCI
    -0.25
    夹
    -0.25
    _cou
    -0.25
    èĴ¸æ±½
    -0.25
    POSITIVE LOGITS
    -l
    0.42
    _l
    0.33
    .l
    0.31
    æĬ¬å¤´
    0.30
    L
    0.28
     L
    0.27
    ä¸ĥæĺŁ
    0.27
    ï½Į
    0.26
    <l
    0.26
    lis
    0.26
    Activations Density 0.109%

    No Known Activations