© 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. 54618
    Prev
    Next
    INDEX
    Explanations

    sol

    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
    åķĨçĶ¨
    -0.31
    è¹Ī
    -0.31
    uste
    -0.27
    conj
    -0.26
    æķĻèĤ²åŁ¹è®Ń
    -0.26
    indx
    -0.25
    lex
    -0.25
     nipples
    -0.25
    岬
    -0.24
    è¯įæĿ¡
    -0.24
    POSITIVE LOGITS
    strength
    0.27
    atel
    0.27
    ató
    0.27
     strength
    0.27
     Strength
    0.26
     qb
    0.25
     fib
    0.25
     Fib
    0.25
    ub
    0.25
     spin
    0.24
    Activations Density 0.007%

    No Known Activations