© 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. 32-TRANSCODER-HP
    7. 42640
    Prev
    Next
    INDEX
    Explanations

    people and accomplishments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æłª
    -0.28
    знаÑĩ
    -0.26
    çīĩ
    -0.26
    éĺ¶çº§
    -0.25
    æį®
    -0.24
     List
    -0.23
    å¤±æľĽ
    -0.23
    æ²ĥ
    -0.23
    纷
    -0.23
    ACT
    -0.23
    POSITIVE LOGITS
     formed
    0.40
    沿
    0.39
     produced
    0.37
     along
    0.36
     Along
    0.34
     supported
    0.33
     facilitated
    0.33
    along
    0.32
     caused
    0.31
     sold
    0.31
    Activations Density 0.009%

    No Known Activations