© 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. 54602
    Prev
    Next
    INDEX
    Explanations

    mining

    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
    Negative Logits
    eres
    -0.30
    åĴ¬
    -0.26
     boiler
    -0.26
    erm
    -0.25
     Vital
    -0.24
    çĶ«
    -0.24
    од
    -0.24
    _under
    -0.24
     ret
    -0.24
     bem
    -0.24
    POSITIVE LOGITS
    wik
    0.30
     rant
    0.27
     resist
    0.25
    opol
    0.25
    plan
    0.25
    æµģè¡Į
    0.25
    ]-$
    0.24
    æµģåŁŁ
    0.24
     ata
    0.24
     plague
    0.24
    Activations Density 0.009%

    No Known Activations