© 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. 56804
    Prev
    Next
    INDEX
    Explanations

    school

    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
    ç±»
    -0.25
    ajo
    -0.24
    angi
    -0.24
     classes
    -0.24
    éĺ¶æ®µ
    -0.24
    éĻIJ度
    -0.23
    ç¦ģåĮº
    -0.23
    Classes
    -0.23
    resses
    -0.23
    haus
    -0.22
    POSITIVE LOGITS
    dent
    0.27
    æİıåĩº
    0.26
    ify
    0.25
    rawler
    0.25
     Mim
    0.25
     Ruiz
    0.24
    太太
    0.24
    ilian
    0.24
     implementing
    0.24
    gun
    0.23
    Activations Density 0.002%

    No Known Activations