© 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. 98849
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    éĩįå·¥
    -0.27
    åħ¶ä»ĸçļĦ
    -0.26
    åĨįæĿ¥
    -0.26
    åħ¶ä»ĸ人
    -0.25
    pragma
    -0.25
     Pvt
    -0.25
    other
    -0.24
     organisers
    -0.24
    æĺ¯éŁ©åĽ½
    -0.24
    аÑĤелÑĮ
    -0.24
    POSITIVE LOGITS
     EM
    0.31
    ish
    0.26
    éĶŃ
    0.25
    ty
    0.25
     ваÑĪего
    0.25
    asha
    0.24
    æĦıè§ģ建议
    0.23
    unu
    0.23
     Suk
    0.23
    sto
    0.23
    Activations Density 0.008%

    No Known Activations