© 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. 130728
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
    æĥ³èµ·
    -0.32
    æĥ³åĪ°äºĨ
    -0.31
    æĥ³åĪ°
    -0.30
    è¿ijæĹ¥
    -0.28
    utive
    -0.28
    æĹ¥åīį
    -0.27
     thinking
    -0.27
    æĪijåıĪ
    -0.27
    æĥ³èµ·äºĨ
    -0.26
    uted
    -0.25
    POSITIVE LOGITS
    没åħ³ç³»
    0.53
    ä¸įå¾Ĺ
    0.31
    ä¸įè¦ģ
    0.30
     don
    0.29
    ä¸įä¼ļ
    0.28
    ä¸įçĶ¨æĭħå¿ĥ
    0.28
     Don
    0.28
     principal
    0.27
    æŀ¶
    0.27
    åıªè¦ģ
    0.26
    Activations Density 0.012%

    No Known Activations