© 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. 30-TRANSCODER-HP
    7. 96568
    Prev
    Next
    INDEX
    Explanations

    Authors and accomplishments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arer
    -0.31
    isans
    -0.27
     Ere
    -0.25
    posable
    -0.25
    æľī趣çļĦ
    -0.25
    avig
    -0.24
    ermen
    -0.24
    moment
    -0.24
    dana
    -0.24
    umps
    -0.24
    POSITIVE LOGITS
     tongues
    0.26
     forensic
    0.26
    åĽ¢è´Ń
    0.26
    åĨ¶éĩij
    0.25
    ãĥĻãĤ¹ãĥĪ
    0.25
    åĮ»åѦ
    0.25
     best
    0.25
     publi
    0.25
    storeId
    0.25
    ually
    0.24
    Activations Density 0.894%

    No Known Activations