© 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. 27-TRANSCODER-HP
    7. 9486
    Prev
    Next
    INDEX
    Explanations

    went

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laz
    -0.28
     proceeds
    -0.27
     thing
    -0.27
    izzy
    -0.27
     proceed
    -0.27
     stays
    -0.26
    колÑĮ
    -0.26
    å½ĵä¹ĭæĹłæĦ§
    -0.26
    entially
    -0.26
     stay
    -0.26
    POSITIVE LOGITS
    夫å¦ĩ
    0.28
     Nass
    0.27
    awl
    0.26
    æĬ¤åį«
    0.26
    rawl
    0.25
     Kauf
    0.25
    å·ŀ
    0.25
    çıŀ
    0.25
    cess
    0.25
    chw
    0.24
    Activations Density 0.000%

    No Known Activations