© 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. 20-TRANSCODER-HP
    7. 64490
    Prev
    Next
    INDEX
    Explanations

    bar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampoo
    -0.30
    æĢ»ä¼ļ
    -0.28
    æĹ¶è¡¨ç¤º
    -0.27
    möglich
    -0.26
    åıĹåĪ°äºĨ
    -0.26
     Goose
    -0.26
    ä¸Ģæīĭ
    -0.25
    kı
    -0.25
    éĥ½ä¼ļ
    -0.25
    éĥ½
    -0.25
    POSITIVE LOGITS
    RON
    0.28
    æŃ»è§Ĵ
    0.26
    zb
    0.26
    æľĭåıĭ们对
    0.25
    /navigation
    0.25
    æĪIJçĨŁ
    0.24
    Frameworks
    0.24
     Authorities
    0.24
    fq
    0.24
    za
    0.24
    Activations Density 21.776%

    No Known Activations