© 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. 23-TRANSCODER-HP
    7. 24392
    Prev
    Next
    INDEX
    Explanations

    are/increasingly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edral
    -0.28
    orra
    -0.27
     swell
    -0.26
    æĻ®éģįåŃĺåľ¨
    -0.26
    éģĹæĨ¾
    -0.26
    ride
    -0.26
    ä¸įæĪIJ
    -0.26
    å¹²éĥ¨éĺŁä¼į
    -0.25
     Glo
    -0.25
    rick
    -0.25
    POSITIVE LOGITS
    éĩĩçĶ¨äºĨ
    0.28
     adopts
    0.28
    AndGet
    0.28
    éĩĩçĶ¨
    0.28
    ogui
    0.27
     Modi
    0.26
    ymoon
    0.26
    çĶ¨äºĨ
    0.26
    éĢīçĶ¨
    0.26
    å¹´çĶ±
    0.26
    Activations Density 0.006%

    No Known Activations