© 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. 22805
    Prev
    Next
    INDEX
    Explanations

    Wake/Vik names and waking

    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
    çŁŃçŁŃ
    -0.28
    pered
    -0.28
     shortened
    -0.27
     region
    -0.26
    argas
    -0.26
    anted
    -0.25
    èģŀãģį
    -0.25
    KS
    -0.25
    çĥŃè¡Ģ
    -0.25
    story
    -0.25
    POSITIVE LOGITS
    esses
    0.29
     @{
    0.27
     @{↵
    0.26
     altogether
    0.25
    éĻĦ件
    0.24
     @{$
    0.24
     Tee
    0.24
     SEN
    0.23
    [array
    0.23
    	timeout
    0.23
    Activations Density 0.002%

    No Known Activations