© 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. 32-TRANSCODER-HP
    7. 43768
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ign
    -0.29
    纪
    -0.27
    IGN
    -0.27
    PECT
    -0.26
     Serg
    -0.25
     Ign
    -0.25
    çĶµåĬĽ
    -0.25
    _OW
    -0.25
    },'
    -0.24
     Lingu
    -0.24
    POSITIVE LOGITS
     those
    0.30
    åı£
    0.27
    science
    0.25
    æ¡Ī
    0.25
    çļĦè·Ŀ离
    0.25
     case
    0.24
    those
    0.24
    .AttributeSet
    0.24
    èµĶ
    0.24
    éľ¹
    0.24
    Activations Density 0.035%

    No Known Activations