© 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. 20-TRANSCODER-HP
    7. 129981
    Prev
    Next
    INDEX
    Explanations

    Feelings, sensations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icontrol
    -0.29
    frei
    -0.28
    çĶŁæ´»çļĦ
    -0.26
    ÑĤика
    -0.26
    venues
    -0.25
    WithOptions
    -0.25
     thigh
    -0.25
     zwar
    -0.24
    å½ĵåľ°çļĦ
    -0.24
    åĨ°åĨ·
    -0.24
    POSITIVE LOGITS
    æļĹ
    0.27
    Ñĥж
    0.25
    him
    0.24
    æ¯Ķäºļ
    0.24
    ç«Ļ
    0.24
    egral
    0.24
    aits
    0.24
     viol
    0.24
    akit
    0.23
    è¯Ħè®®
    0.23
    Activations Density 15.512%

    No Known Activations