© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13342
    Prev
    Next
    INDEX
    Explanations

    things holy, hellz bellz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŃł
    -0.22
    çijŁ
    -0.21
    沿
    -0.19
    LETE
    -0.19
    legg
    -0.19
    åħĪè¡Į
    -0.18
    å®ľ
    -0.18
    èĭĶ
    -0.18
    imals
    -0.18
    æĽ´å¤ļ
    -0.18
    POSITIVE LOGITS
    adic
    0.23
    æĪij对
    0.21
    æİı
    0.20
    æĪij没
    0.20
    æī°ä¹±
    0.19
    ady
    0.19
     Sale
    0.19
    umbo
    0.18
    !
    0.18
    (validation
    0.18
    Activations Density 0.025%

    No Known Activations