© 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. 87428
    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
     Zak
    -0.26
    æĺİç¡®
    -0.25
    çݯèĬĤ
    -0.24
    带éĺŁ
    -0.24
    weg
    -0.23
    ritch
    -0.23
    posables
    -0.23
    sson
    -0.23
     sensors
    -0.23
     bones
    -0.22
    POSITIVE LOGITS
    ä¸įå¿ħ
    0.34
    ä¸į代表
    0.30
    并ä¸į代表
    0.30
    ä¸įå½±åĵį
    0.29
    edException
    0.28
    并ä¸įèĥ½
    0.28
    ä¸įåģļ
    0.27
     endorsements
    0.26
     neither
    0.26
    ä¸įçĶ¨
    0.26
    Activations Density 0.044%

    No Known Activations