© 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. 27-TRANSCODER-HP
    7. 8847
    Prev
    Next
    INDEX
    Explanations

    technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boxed
    -0.32
    hra
    -0.30
    üb
    -0.27
    iban
    -0.27
    éļĨ
    -0.26
    stin
    -0.25
    æıIJåĢ¡
    -0.25
    cea
    -0.25
     cons
    -0.24
     Force
    -0.24
    POSITIVE LOGITS
    没äºĨ
    0.26
    imity
    0.26
    没ä»Ģä¹Ī
    0.26
    æŀģ度
    0.26
    åıĺå¾ĹæĽ´
    0.26
    (jj
    0.26
    icious
    0.25
    бой
    0.24
     orthogonal
    0.24
    两çĤ¹
    0.24
    Activations Density 0.001%

    No Known Activations