© 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. 43313
    Prev
    Next
    INDEX
    Explanations

    Incoherent or fragmented text

    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
    iangle
    -0.28
     ref
    -0.26
    å¾ĭ
    -0.26
    aju
    -0.26
    duk
    -0.26
    éĵĹ
    -0.25
     öde
    -0.25
    ÑģÑĥд
    -0.25
    ä¸ŃéĹ´
    -0.25
     tải
    -0.24
    POSITIVE LOGITS
    ead
    0.30
     anticipated
    0.27
    æ´ª
    0.27
    irá
    0.26
    èªĵ
    0.26
     OrderedDict
    0.25
    crap
    0.25
    ante
    0.25
    ournals
    0.25
    áp
    0.25
    Activations Density 0.006%

    No Known Activations