© 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. 24-TRANSCODER-HP
    7. 149759
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°½åı¯èĥ½
    -0.34
    å°½éĩı
    -0.31
     carefully
    -0.30
    eded
    -0.30
    å°½æĹ©
    -0.29
    æĽ´å¥½çļĦ
    -0.28
    åĬĽäºī
    -0.27
     counters
    -0.26
     careful
    -0.25
     honest
    -0.25
    POSITIVE LOGITS
    æľīäºĽ
    0.35
    æľī大éĩıçļĦ
    0.34
    æľīä¸ĢäºĽ
    0.33
    æľī许å¤ļ
    0.32
    æľīå¾Īå¤ļ
    0.31
    æľīçļĦ
    0.30
    ç¹ģå¿Ļ
    0.30
    æľīä¸Ģ
    0.28
    éĿŀ常å¤ļ
    0.28
    æľīå¤ļ
    0.28
    Activations Density 0.898%

    No Known Activations