© 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. 111673
    Prev
    Next
    INDEX
    Explanations

    Alternating, alternative

    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
    äººåľ¨
    -0.31
     person
    -0.29
    人æĢ§
    -0.28
    æĸ¹ä¾¿
    -0.28
    è§Ĩ为
    -0.26
    管çIJĨæ°´å¹³
    -0.26
    ä¸įå½±åĵį
    -0.26
    æ¶Ī
    -0.26
    ä¿ĿåŃĺ
    -0.25
    被è§Ĩ为
    -0.25
    POSITIVE LOGITS
    ometric
    0.28
    ubits
    0.27
    é»ĺé»ĺ
    0.26
    ward
    0.25
     unnamed
    0.24
    allback
    0.24
    èĥĮéĿ¢
    0.24
    .nano
    0.24
    è´¸
    0.23
    ificance
    0.23
    Activations Density 0.007%

    No Known Activations