© 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. 88235
    Prev
    Next
    INDEX
    Explanations

    ought

    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
    íĭ°
    -0.31
     (('
    -0.27
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    -0.27
    çļĦèģĮä¸ļ
    -0.26
    .rar
    -0.26
    ä¸įç»ı
    -0.26
    æĺ¯ä¸Ģ项
    -0.25
    mlink
    -0.25
    产åĵģè´¨éĩı
    -0.24
    usage
    -0.24
    POSITIVE LOGITS
    åŃIJ
    0.30
    æŀĭ
    0.28
    apot
    0.27
    much
    0.25
    çĽ¥
    0.25
    OTS
    0.24
    ä¸ĩçī©
    0.24
    null
    0.24
    å·±
    0.24
    illery
    0.24
    Activations Density 0.123%

    No Known Activations