© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161646
    Prev
    Next
    INDEX
    Explanations

    custom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ck
    -0.28
    ksen
    -0.28
    enery
    -0.25
    ائÙĨ
    -0.25
    ħį
    -0.25
    è°ĥéħį
    -0.25
     discrim
    -0.24
    è°ĥ
    -0.24
    èĩ³
    -0.24
    使åħ¶
    -0.24
    POSITIVE LOGITS
    izes
    0.29
    ORK
    0.27
    é¢ĦæľŁ
    0.25
     Content
    0.25
     Cata
    0.25
     Cure
    0.24
    WindowText
    0.24
    lena
    0.24
     luck
    0.24
    verständlich
    0.24
    Activations Density 0.009%

    No Known Activations