© 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. 54440
    Prev
    Next
    INDEX
    Explanations

    say "rights"

    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
    æľīåĩłä¸ª
    -0.27
    filesize
    -0.27
    (XML
    -0.25
    zier
    -0.25
    ULER
    -0.24
    ä¿Ĭ
    -0.24
    ÅĤoż
    -0.24
     Stmt
    -0.24
    å¢ĥ
    -0.24
    没æĶ¶
    -0.23
    POSITIVE LOGITS
     pains
    0.28
     trailing
    0.28
    pee
    0.25
    tring
    0.25
     dist
    0.25
    èģĭ
    0.25
     stellen
    0.25
     downright
    0.24
    -around
    0.24
    elman
    0.24
    Activations Density 0.011%

    No Known Activations