© 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. 9-TRANSCODER-HP
    7. 30213
    Prev
    Next
    INDEX
    Explanations

    picking up items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     whe
    -0.29
    éĥ¨éĥ¨éķ¿
    -0.28
    berger
    -0.26
    åIJĪä½ľ
    -0.26
    è¯Ŀ说
    -0.26
     semen
    -0.25
    åĵģ
    -0.25
     eyed
    -0.25
    angan
    -0.25
    iol
    -0.25
    POSITIVE LOGITS
    .AddComponent
    0.26
    åĩij
    0.26
    çī¢è®°
    0.25
    ĪæĿĥ
    0.25
     lowercase
    0.25
    ognito
    0.25
    æ²³æµģåŁŁ
    0.24
    .GetResponse
    0.24
    èĶ½
    0.24
    两家
    0.24
    Activations Density 0.889%

    No Known Activations