© 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. 33-TRANSCODER-HP
    7. 54284
    Prev
    Next
    INDEX
    Explanations

    Obtaining and legal jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igue
    -0.30
    ools
    -0.28
    èļ±
    -0.26
     An
    -0.25
    Alarm
    -0.25
    åijĬ
    -0.25
    æ±ł
    -0.25
    uling
    -0.24
    An
    -0.24
    ely
    -0.24
    POSITIVE LOGITS
    管å±Ģ
    0.30
     Ring
    0.28
    åľ°ä¸ĭ
    0.26
    ç»Ļ人
    0.26
     unloaded
    0.25
    _ring
    0.25
     ring
    0.25
     sideways
    0.25
     Osborne
    0.25
     CLOSED
    0.24
    Activations Density 0.007%

    No Known Activations