© 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. 33-TRANSCODER-HP
    7. 53139
    Prev
    Next
    INDEX
    Explanations

    scientific language

    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
     organ
    -0.46
     substituted
    -0.42
    ary
    -0.39
     ary
    -0.38
    organ
    -0.38
    bor
    -0.37
     phen
    -0.35
     diary
    -0.35
    phen
    -0.35
     al
    -0.33
    POSITIVE LOGITS
    çĽ²
    0.35
    æĦļ
    0.30
     upside
    0.28
    æĪIJçĨŁ
    0.28
    èĤ²
    0.27
     blind
    0.27
     forged
    0.24
    人身
    0.24
    kul
    0.24
    åľŁ
    0.24
    Activations Density 0.422%

    No Known Activations