© 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. 22-TRANSCODER-HP
    7. 129377
    Prev
    Next
    INDEX
    Explanations

    limitations and constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upfront
    -0.51
     initial
    -0.50
    æľĢåĪĿçļĦ
    -0.50
    åīįæľŁ
    -0.48
    åĪĿæľŁ
    -0.48
    åħĪ
    -0.47
     beforehand
    -0.47
     initially
    -0.47
    æĹ©æľŁ
    -0.46
    æľĢåĪĿ
    -0.45
    POSITIVE LOGITS
     later
    0.50
     after
    0.49
    åIJİ
    0.49
     afterwards
    0.47
     After
    0.46
    äºĭåIJİ
    0.46
    åIJİæľŁ
    0.46
    æĹ¥åIJİ
    0.45
    åIJİç»Ń
    0.45
    After
    0.44
    Activations Density 0.004%

    No Known Activations