© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54209
    Prev
    Next
    INDEX
    Explanations

    pulling / -ing

    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
    where
    -0.31
    èĩ£
    -0.31
     where
    -0.31
    ÙĦاء
    -0.29
    æĪijä¸įæĥ³
    -0.27
    us
    -0.27
    æĪijå¾Ī
    -0.27
    %
    -0.26
    ®
    -0.26
    ca
    -0.26
    POSITIVE LOGITS
     aside
    0.30
     apart
    0.30
     tabs
    0.28
     bou
    0.26
     aggressively
    0.26
    =out
    0.26
     bolts
    0.25
    DownList
    0.25
    icons
    0.25
    )(↵
    0.25
    Activations Density 0.010%

    No Known Activations