© 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. 30-TRANSCODER-HP
    7. 96429
    Prev
    Next
    INDEX
    Explanations

    Reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     next
    -0.29
    EUR
    -0.26
     entire
    -0.26
    æĶ¸
    -0.25
     built
    -0.25
    akit
    -0.25
    èĽ¤
    -0.24
    catch
    -0.24
    =back
    -0.24
     Stout
    -0.23
    POSITIVE LOGITS
    åħ±
    0.29
    许
    0.29
    åĩŃ
    0.27
    знаÑĩ
    0.27
    dire
    0.26
    許
    0.26
    ä¼ī
    0.26
    èĩªçĶ±è´¸æĺĵ
    0.25
    encies
    0.25
    sigma
    0.25
    Activations Density 0.797%

    No Known Activations