© 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. 27-TRANSCODER-HP
    7. 8978
    Prev
    Next
    INDEX
    Explanations

    Turn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chter
    -0.30
     cleared
    -0.27
     pilot
    -0.25
    æĪĸå¤ļ
    -0.25
    Lite
    -0.24
     grilled
    -0.24
    è¯·ä½ł
    -0.24
    çĹ£
    -0.24
    ald
    -0.23
     convicted
    -0.23
    POSITIVE LOGITS
    -TV
    0.29
    pell
    0.26
    éĤ®å¯Ħ
    0.26
    nas
    0.26
    åıĹçĽĬ
    0.25
    uese
    0.24
    atak
    0.24
    odox
    0.24
    ç»Ī
    0.24
    çĥŃ带
    0.24
    Activations Density 1.108%

    No Known Activations