© 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. 54693
    Prev
    Next
    INDEX
    Explanations

    V

    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
    adians
    -0.28
     Maurit
    -0.27
    reak
    -0.27
    -flag
    -0.26
    athers
    -0.26
    èĤ®
    -0.26
     JT
    -0.25
    anst
    -0.25
    REAK
    -0.25
    ç»ĦåĽ¾
    -0.25
    POSITIVE LOGITS
    Lower
    0.30
     am
    0.28
    ä¿Ŀ
    0.28
     }}/
    0.26
    å®ŀ
    0.26
     Lower
    0.26
    oc
    0.26
     realized
    0.25
    ibo
    0.25
     al
    0.25
    Activations Density 0.015%

    No Known Activations