© 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. 43197
    Prev
    Next
    INDEX
    Explanations

    any

    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
    ains
    -0.27
    kers
    -0.26
     miá»ħn
    -0.26
     thái
    -0.25
    ktor
    -0.25
    Registr
    -0.25
     INTERVAL
    -0.25
    ieres
    -0.25
    istogram
    -0.25
    bers
    -0.24
    POSITIVE LOGITS
    éĥ¨åī¯éĥ¨éķ¿
    0.32
    å±Ģåī¯å±Ģéķ¿
    0.31
     pinch
    0.31
    å±Ģ
    0.28
     act
    0.28
    å±Ģå±Ģéķ¿
    0.27
     blow
    0.27
    sharp
    0.26
    åºŃ
    0.26
    asm
    0.26
    Activations Density 0.000%

    No Known Activations