© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52565
    Prev
    Next
    INDEX
    Explanations

    comm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    cord
    -0.34
     effect
    -0.32
    erti
    -0.28
     effects
    -0.27
    -effect
    -0.27
    tip
    -0.26
    æī°
    -0.26
    ña
    -0.25
    OLUM
    -0.25
     mum
    -0.25
    POSITIVE LOGITS
    uite
    0.29
    uve
    0.27
    ino
    0.26
    ually
    0.26
    ä¸Ģ个éĹ®é¢ĺ
    0.26
    utable
    0.25
    éĶĢ
    0.25
    å³Ĵ
    0.25
    ä¿¡åı·
    0.25
    å¼Ģåĩº
    0.24
    Activations Density 0.004%

    No Known Activations