© 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. 53204
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, and foreign words

    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
    iter
    -0.30
     Disco
    -0.28
     VC
    -0.27
     inv
    -0.26
     Stat
    -0.26
    STAT
    -0.26
     disco
    -0.25
    éĿ©
    -0.25
    æ°ij
    -0.25
    åķĨ
    -0.25
    POSITIVE LOGITS
     erect
    0.28
     hObject
    0.27
     Blank
    0.26
    nage
    0.25
    meld
    0.24
    çĸĹ
    0.24
    åĩĮæĻ¨
    0.24
    abella
    0.24
    osis
    0.23
    اسÙĦ
    0.23
    Activations Density 0.015%

    No Known Activations