© 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. 41819
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
     Rai
    -0.28
    æļĤ
    -0.27
    ialog
    -0.27
    æļ«
    -0.26
    oha
    -0.25
    éĺĻ
    -0.25
    soever
    -0.25
     catch
    -0.24
     Radi
    -0.24
     radi
    -0.24
    POSITIVE LOGITS
    æ±Łå±±
    0.26
    habit
    0.25
     nymph
    0.24
     Infant
    0.24
    quine
    0.24
    onas
    0.24
    ç¿İ
    0.24
    Sharper
    0.23
     ÑĥÑĢовне
    0.23
    ãĥĪãĥ³
    0.23
    Activations Density 0.002%

    No Known Activations