© 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. 42939
    Prev
    Next
    INDEX
    Explanations

    say "the ending ache"

    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
    eor
    -0.30
    astos
    -0.28
    oris
    -0.28
    agos
    -0.28
    inks
    -0.27
    asts
    -0.26
    aded
    -0.26
     Kont
    -0.25
    afari
    -0.25
     phased
    -0.25
    POSITIVE LOGITS
    éĵ²
    0.27
    èŀ¯
    0.27
    ä¸ľè·¯
    0.26
     tent
    0.25
    åĽ½å®¶éĺŁ
    0.25
    liquid
    0.24
     tol
    0.24
    isel
    0.24
    Ben
    0.23
     cha
    0.23
    Activations Density 0.003%

    No Known Activations