© 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. 27-TRANSCODER-HP
    7. 8788
    Prev
    Next
    INDEX
    Explanations

    research and development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     places
    -0.32
    éĤ£äºĽ
    -0.28
     Places
    -0.27
    å³»
    -0.27
    places
    -0.27
    æĶ¾ç½®
    -0.27
    çļĦåľ°æĸ¹
    -0.26
    Places
    -0.26
    åįĩ
    -0.26
     lugares
    -0.26
    POSITIVE LOGITS
     roma
    0.35
    ablo
    0.29
     novel
    0.29
     breakthrough
    0.28
     Novel
    0.28
    JNIEnv
    0.28
    æľįåĬ¡æ°´å¹³
    0.27
    tera
    0.27
     innovation
    0.27
     astonishing
    0.26
    Activations Density 0.044%

    No Known Activations