© 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. 42153
    Prev
    Next
    INDEX
    Explanations

    say "1"

    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
    æĶ¯çº¿
    -0.25
    elia
    -0.24
    opsis
    -0.24
    "<?
    -0.24
    akov
    -0.23
    èįĥ
    -0.23
    yny
    -0.23
    xee
    -0.23
     fragment
    -0.23
    pch
    -0.23
    POSITIVE LOGITS
    åIJĬ
    0.33
    åıij
    0.30
     brow
    0.28
     estimating
    0.27
    èĤīç±»
    0.26
    åĪ·æĸ°
    0.26
    çģ«æĺŁ
    0.26
    æķ°
    0.26
    stack
    0.26
    bor
    0.25
    Activations Density 0.002%

    No Known Activations