© 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. 87313
    Prev
    Next
    INDEX
    Explanations

    flies

    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
     hott
    -0.26
     Haz
    -0.26
    -prefix
    -0.25
    maj
    -0.25
     hus
    -0.24
    MS
    -0.24
    wolf
    -0.24
     маÑģÑĤ
    -0.23
    çĻ¾å®¶
    -0.23
    .prefix
    -0.23
    POSITIVE LOGITS
    edb
    0.31
    æĭį
    0.27
     comm
    0.26
    åĶ¤
    0.26
    å´©æºĥ
    0.26
    è¶ĭ
    0.26
    à®Ł
    0.26
     precise
    0.25
    å·¦åı³
    0.25
    æĶ¾
    0.25
    Activations Density 0.043%

    No Known Activations