© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52908
    Prev
    Next
    INDEX
    Explanations

    (

    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
    )m
    -0.29
    eson
    -0.28
    ages
    -0.27
    ä¸ŃåĽ½å¤§éĻĨ
    -0.26
    	ad
    -0.25
    chter
    -0.25
    eting
    -0.25
    )object
    -0.24
    actics
    -0.24
    ãģķãĤī
    -0.24
    POSITIVE LOGITS
     sold
    0.28
     neatly
    0.28
     Ñĥдален
    0.28
     pierced
    0.27
    osaurs
    0.26
     Weaver
    0.26
    online
    0.26
    使ä¹ĭ
    0.25
    åĶ®
    0.25
     cond
    0.25
    Activations Density 0.008%

    No Known Activations