© 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. 41606
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .enqueue
    -0.27
    æĿĥ
    -0.26
    ativas
    -0.25
     pari
    -0.25
    icals
    -0.25
    å°Ŀ
    -0.25
    æ¬Ĭ
    -0.25
    pany
    -0.24
    avers
    -0.24
     plays
    -0.24
    POSITIVE LOGITS
    mailer
    0.27
    sms
    0.26
     Acad
    0.25
    ÅĪ
    0.25
    ski
    0.24
    ignite
    0.24
     Somerset
    0.23
     prez
    0.23
     Bulld
    0.23
    wend
    0.23
    Activations Density 0.001%

    No Known Activations