© 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. 35-TRANSCODER-HP
    7. 40236
    Prev
    Next
    INDEX
    Explanations

    non-english or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīçļĦ
    -0.31
    earer
    -0.25
    arel
    -0.23
    Į¨
    -0.23
    æģ¯
    -0.23
     listener
    -0.23
    é£İæ°Ķ
    -0.23
    _INTR
    -0.23
    AccessException
    -0.23
    ë°§
    -0.23
    POSITIVE LOGITS
    oval
    0.29
     oval
    0.27
    еÑĢж
    0.27
    æ¦Ľ
    0.26
    unc
    0.26
    æĶ¾å¤§
    0.26
    ockey
    0.25
    /story
    0.25
     Olson
    0.25
     VERY
    0.24
    Activations Density 2.238%

    No Known Activations