© 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. 30-TRANSCODER-HP
    7. 95981
    Prev
    Next
    INDEX
    Explanations

    strengthen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ¢åįł
    -0.28
    强åĮĸ
    -0.28
    æī¿
    -0.27
    ä¸Ģè§Ī
    -0.27
    æľĢ强
    -0.26
    è¾ĥ强çļĦ
    -0.26
    stärke
    -0.26
    æIJŃä¹ĺ
    -0.26
    强çĥĪçļĦ
    -0.26
    åĬłåĽº
    -0.26
    POSITIVE LOGITS
     those
    0.43
     ties
    0.41
     the
    0.36
     relationships
    0.36
     their
    0.35
     associations
    0.33
     links
    0.33
     connection
    0.33
     association
    0.32
     link
    0.31
    Activations Density 0.104%

    No Known Activations