© 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. 112119
    Prev
    Next
    INDEX
    Explanations

    Religious texts

    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
     forget
    -0.27
    elocity
    -0.26
    é¦Ļ
    -0.25
    转载请
    -0.24
    whelming
    -0.24
     visibly
    -0.23
    cac
    -0.23
     angel
    -0.23
     obviously
    -0.23
     middle
    -0.23
    POSITIVE LOGITS
    -AA
    0.26
    finity
    0.26
    еÑĤÑĮ
    0.25
    жал
    0.25
    æĮģä¹ħ
    0.24
    -save
    0.24
    etr
    0.24
    Saved
    0.24
    FRAME
    0.23
    USES
    0.23
    Activations Density 0.007%

    No Known Activations