© 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. 96736
    Prev
    Next
    INDEX
    Explanations

    royalty/kingdoms

    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
     Aut
    -0.28
    üst
    -0.25
    'aut
    -0.25
     BED
    -0.25
    elt
    -0.24
    IOC
    -0.24
    æ¡ĮåŃIJä¸Ĭ
    -0.24
     Morr
    -0.24
    ircular
    -0.24
    ’aut
    -0.23
    POSITIVE LOGITS
    cular
    0.28
     thủy
    0.25
    illos
    0.25
    ен
    0.25
    éģ¥
    0.25
    åįī
    0.25
     setSupportActionBar
    0.24
     Covered
    0.24
     euro
    0.24
     Trom
    0.24
    Activations Density 0.101%

    No Known Activations