© 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. 54457
    Prev
    Next
    INDEX
    Explanations

    Technical and medical contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aan
    -0.28
    mö
    -0.27
    (exc
    -0.26
    OnInit
    -0.26
    XP
    -0.25
    ãĥľãĥ¼ãĥī
    -0.25
    	esc
    -0.25
    _supply
    -0.24
     excit
    -0.24
     Expires
    -0.24
    POSITIVE LOGITS
     fr
    0.35
     oc
    0.28
    沧
    0.28
     disease
    0.28
    dom
    0.28
     dirt
    0.28
     DOM
    0.27
    olib
    0.27
     maj
    0.26
     UC
    0.26
    Activations Density 0.008%

    No Known Activations