© 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. 98243
    Prev
    Next
    INDEX
    Explanations

    farm

    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
    omers
    -0.27
    ascar
    -0.27
    verages
    -0.26
    rame
    -0.26
    zar
    -0.25
    EAR
    -0.25
    ä¸įéĢĤåIJĪ
    -0.24
    çĹķ
    -0.24
    å°Ķ
    -0.24
    ffects
    -0.23
    POSITIVE LOGITS
    amental
    0.34
    ä½ıåĿĢ
    0.25
    åİķ
    0.25
    sheet
    0.24
    site
    0.24
     elder
    0.24
    acies
    0.23
     hosting
    0.23
    beat
    0.23
     collapse
    0.23
    Activations Density 0.591%

    No Known Activations