© 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. 52878
    Prev
    Next
    INDEX
    Explanations

    ad

    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
     Organ
    -0.27
    adow
    -0.27
    ar
    -0.27
    èģĶ
    -0.27
    é£ŀ
    -0.25
    éĴĪ
    -0.25
    ç»Ŀ
    -0.25
    ãģĵ
    -0.25
    .co
    -0.25
    æIJŃ
    -0.24
    POSITIVE LOGITS
     network
    0.30
    tober
    0.30
    ÑģÑħод
    0.29
    Network
    0.28
    NETWORK
    0.28
    network
    0.27
    verting
    0.27
    влеÑĩен
    0.27
    venient
    0.27
    version
    0.27
    Activations Density 0.014%

    No Known Activations