© 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. 20-TRANSCODER-HP
    7. 129457
    Prev
    Next
    INDEX
    Explanations

    Source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ĭ称
    -0.31
    æ²®
    -0.29
    ä¹Łæĺ¯å¦ĤæѤ
    -0.29
    äºİæѤ
    -0.28
    íĸī
    -0.28
    ä¸į足
    -0.27
    èĩ³æѤ
    -0.27
    ä¹Łéļıä¹ĭ
    -0.26
    ollower
    -0.26
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.26
    POSITIVE LOGITS
    çĶ³
    0.26
    umen
    0.25
    å¼ĢçĽĺ
    0.25
    acad
    0.25
    ìĺ
    0.24
    á»ı
    0.24
    çĥ
    0.24
    oya
    0.24
     mark
    0.23
    иÑĤелÑĮ
    0.23
    Activations Density 42.637%

    No Known Activations