© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96961
    Prev
    Next
    INDEX
    Explanations

    partnership

    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
    Negative Logits
    èģĶåIJĪ
    -0.45
    åIJĪä½ľ
    -0.41
    çļĦåIJĪä½ľ
    -0.40
    èģ¯åIJĪ
    -0.39
     joint
    -0.38
     collaborative
    -0.36
    åįıåIJĮ
    -0.36
     Joint
    -0.35
     collaboration
    -0.35
     jointly
    -0.34
    POSITIVE LOGITS
     inter
    0.37
    åħ¶ä»ĸçļĦ
    0.31
    åħ¶ä»ĸ
    0.31
     gratuita
    0.29
     ander
    0.28
     with
    0.28
    åħ¶å®ĥ
    0.28
    è·¨
    0.27
    .with
    0.27
    with
    0.27
    Activations Density 0.117%

    No Known Activations