© 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. 88388
    Prev
    Next
    INDEX
    Explanations

    potential, possible

    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
    åı¯èĥ½å¯¼èĩ´
    -0.34
    åı¯èĥ½åŃĺåľ¨
    -0.31
    åı¯èĥ½åĩºçİ°
    -0.31
     potentially
    -0.31
    åı¯èĥ½åıijçĶŁ
    -0.30
     possibility
    -0.29
    åı¯èĥ½æľĥ
    -0.28
    æľªå¿ħ
    -0.27
    apy
    -0.27
     possibly
    -0.27
    POSITIVE LOGITS
    langs
    0.27
    纵
    0.27
    åIJ¦
    0.25
    vore
    0.25
    æĹı
    0.25
    å¤ľ
    0.25
    äº
    0.24
    侮辱
    0.24
     corruption
    0.24
    è¿Ŀ
    0.24
    Activations Density 0.023%

    No Known Activations