© 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. 112430
    Prev
    Next
    INDEX
    Explanations

    fields of study

    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
    ',{'
    -0.26
    缸åħ³æĸ°éĹ»
    -0.26
    缼
    -0.26
    è¯Ħä»·
    -0.24
    åĵģå°Ŀ
    -0.24
    selectAll
    -0.24
    éĢīæĭ©
    -0.24
    stk
    -0.23
    æĶ¾åģĩ
    -0.23
    Chr
    -0.23
    POSITIVE LOGITS
    isms
    0.28
     isn
    0.27
    lessness
    0.27
     ÐĽÑİ
    0.26
     occurs
    0.26
     modulo
    0.25
    çĮ¶
    0.25
     via
    0.24
     èĭ¥è¦ģ
    0.24
    synthesize
    0.24
    Activations Density 0.005%

    No Known Activations