© 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. 22347
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
     Tess
    -0.27
     buttonText
    -0.27
    ewidth
    -0.26
    ä¹ŁæŃ£æĺ¯
    -0.26
    æĮī
    -0.26
    cel
    -0.25
    æŃ£æĺ¯
    -0.25
    èĮ¶åĽŃ
    -0.25
    gregated
    -0.25
     steer
    -0.24
    POSITIVE LOGITS
    çªģçĦ¶
    0.26
    è´¤
    0.25
    _deposit
    0.25
     deposit
    0.24
    å´ĩé«ĺ
    0.23
     deposits
    0.23
    æĶ¾åѦ
    0.23
    videos
    0.23
    uent
    0.23
     suddenly
    0.23
    Activations Density 0.009%

    No Known Activations