© 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. 53714
    Prev
    Next
    INDEX
    Explanations

    -ing words

    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
    uts
    -0.30
    itches
    -0.29
    pd
    -0.27
    åĩºåİ»
    -0.27
    ç¼ĵ
    -0.27
     kut
    -0.26
    å¼ĤæĢ§
    -0.26
    èĮĤ
    -0.26
    æľĭ
    -0.26
    ä½Ĩå®ĥ
    -0.26
    POSITIVE LOGITS
     learning
    0.34
     operating
    0.33
     observing
    0.31
     collaborating
    0.31
     working
    0.30
     living
    0.29
     absorbing
    0.29
     interacting
    0.28
    Operating
    0.28
     knowing
    0.28
    Activations Density 0.037%

    No Known Activations