© 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. 54210
    Prev
    Next
    INDEX
    Explanations

    Rob

    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
    utsch
    -0.32
    æ±ĩ
    -0.31
    angu
    -0.27
     Bol
    -0.25
     mou
    -0.24
    Translated
    -0.24
     buc
    -0.24
    éĤ£å°±æĺ¯
    -0.24
    goo
    -0.24
    è½®
    -0.24
    POSITIVE LOGITS
    岸
    0.26
    åĭ
    0.26
    erver
    0.26
    lake
    0.25
    ordable
    0.25
    ees
    0.24
    laces
    0.24
    èŀĪ
    0.24
    yp
    0.24
    aurant
    0.24
    Activations Density 0.009%

    No Known Activations