© 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. 161746
    Prev
    Next
    INDEX
    Explanations

    that

    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
    who
    -0.28
    ISK
    -0.27
     who
    -0.27
    è°ģçŁ¥éģĵ
    -0.26
    which
    -0.26
    para
    -0.26
    еÑĢе
    -0.26
    ers
    -0.25
    -cond
    -0.25
    losure
    -0.25
    POSITIVE LOGITS
     predomin
    0.26
     can
    0.26
     are
    0.25
     conserv
    0.25
    pto
    0.24
    ije
    0.24
     garn
    0.24
    ocrates
    0.24
     is
    0.24
    饧
    0.24
    Activations Density 0.190%

    No Known Activations