© 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. 31-TRANSCODER-HP
    7. 18215
    Prev
    Next
    INDEX
    Explanations

    human

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.32
     extrapol
    -0.25
    ılan
    -0.25
    mon
    -0.25
    è´«
    -0.25
    çĸı
    -0.24
    the
    -0.24
    ities
    -0.24
    tek
    -0.24
    ê·¹
    -0.24
    POSITIVE LOGITS
     CDDL
    0.28
     vere
    0.27
     predicate
    0.27
     appendix
    0.27
    ModelState
    0.25
    éĽĨä½ĵ
    0.25
    nite
    0.25
     inputFile
    0.24
     apocalypse
    0.24
     navigator
    0.24
    Activations Density 0.090%

    No Known Activations