© 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. 22325
    Prev
    Next
    INDEX
    Explanations

    if

    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
    ä½ľåĵģåĨħ容
    -0.29
    ILON
    -0.26
    ä»ĸ们æĺ¯
    -0.26
    å¿ĥåĬ¨
    -0.26
     SOFTWARE
    -0.26
     Handbook
    -0.25
    Tween
    -0.25
    æµģçķħ
    -0.25
     forgive
    -0.25
    å¸ĤæķĻèĤ²å±Ģ
    -0.25
    POSITIVE LOGITS
    é¢Ħ
    0.29
    alist
    0.26
     nerves
    0.25
    ce
    0.25
     yer
    0.25
     parties
    0.25
    eder
    0.24
    è´«ç©·
    0.24
     Pier
    0.24
    ÑıÑģ
    0.24
    Activations Density 0.001%

    No Known Activations