© 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. 54030
    Prev
    Next
    INDEX
    Explanations

    Ment

    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
    ç»ĵ
    -0.28
    ias
    -0.27
    gart
    -0.27
    èĢIJ
    -0.26
    ëĿ¼
    -0.26
    ä¸įéĶĪ
    -0.25
    æĴĴ
    -0.25
     lou
    -0.25
    uni
    -0.25
     quadr
    -0.25
    POSITIVE LOGITS
    ABL
    0.28
    è¹Ī
    0.27
    çĽĴ
    0.27
    éĹ®ä»ĸ
    0.26
    åĶ¯æľī
    0.25
    tw
    0.25
    eve
    0.25
    à§İ
    0.24
    ecome
    0.24
    èĤł
    0.24
    Activations Density 0.003%

    No Known Activations