© 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. 12-TRANSCODER-HP
    7. 22892
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹ®é¢ĺæĺ¯
    -0.29
     hardest
    -0.28
    à¸Ħม
    -0.25
    ãģķãģĦ
    -0.25
    çĶ¥
    -0.25
    å¼Ĥ
    -0.24
    езн
    -0.24
    _mB
    -0.24
    uest
    -0.24
    auled
    -0.24
    POSITIVE LOGITS
    ump
    0.28
     dép
    0.25
    E
    0.24
    ãĥķãĤ£
    0.24
    æłª
    0.24
     local
    0.24
    	yield
    0.24
    rus
    0.23
     personal
    0.23
    è²»
    0.23
    Activations Density 0.001%

    No Known Activations