© 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. 35-TRANSCODER-HP
    7. 40358
    Prev
    Next
    INDEX
    Explanations

    Technical abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASTE
    -0.29
    ÑĪей
    -0.29
    \d
    -0.26
     BAM
    -0.26
    è¿Ļ个è¯į
    -0.25
     MOT
    -0.25
     pockets
    -0.25
    æļ¢
    -0.25
     BI
    -0.25
     kc
    -0.25
    POSITIVE LOGITS
    oz
    0.36
    enen
    0.33
    og
    0.32
    оÑĩ
    0.30
    ig
    0.30
    ol
    0.30
    oth
    0.30
    常è§ģ
    0.29
    ois
    0.29
    ode
    0.28
    Activations Density 0.007%

    No Known Activations