© 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. 43364
    Prev
    Next
    INDEX
    Explanations

    say "oste"

    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
    vented
    -0.27
    thal
    -0.25
     Nev
    -0.25
    ãng
    -0.25
    è´©
    -0.24
    .gener
    -0.24
     endors
    -0.23
     autob
    -0.23
    vern
    -0.23
    pearance
    -0.23
    POSITIVE LOGITS
    REM
    0.30
     oste
    0.29
    ä¹ł
    0.28
     Break
    0.27
     rem
    0.27
    ç¿Ĵ
    0.26
    ãĤªãĤ¹
    0.26
    èħĶ
    0.26
    åħ³èĬĤ
    0.25
     Rem
    0.25
    Activations Density 0.009%

    No Known Activations