© 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. 18-TRANSCODER-HP
    7. 89663
    Prev
    Next
    INDEX
    Explanations

    Dates, numbers, technical details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç´¯
    -0.29
    è¶ħé¢Ŀ
    -0.28
    _cum
    -0.27
    æĦ¿æĻ¯
    -0.27
    cum
    -0.26
    å¢ĥ
    -0.26
    åĢº
    -0.26
     budgets
    -0.26
     forecasts
    -0.25
    plex
    -0.25
    POSITIVE LOGITS
    ##_
    0.26
    éĶ£
    0.25
     vers
    0.25
     thereof
    0.25
    subscription
    0.24
    association
    0.24
    æµĻæ±Łå¤§åѦ
    0.24
    owan
    0.23
    _RESOLUTION
    0.23
     association
    0.23
    Activations Density 18.731%

    No Known Activations