© 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. 57773
    Prev
    Next
    INDEX
    Explanations

    lock

    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
    >Main
    -0.23
    çĥĿ
    -0.23
    è´Łæĭħ
    -0.23
    rule
    -0.23
    æ´ĹèĦ¸
    -0.23
    _FP
    -0.23
    CCCC
    -0.23
    GBT
    -0.22
    çĻĤ
    -0.22
    (resp
    -0.22
    POSITIVE LOGITS
     lock
    1.08
    éĶģ
    1.06
     locks
    1.01
    lock
    0.98
     Lock
    0.95
    Lock
    0.94
    	lock
    0.90
    _lock
    0.90
     locking
    0.90
    -lock
    0.89
    Activations Density 0.006%

    No Known Activations