© 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. 11608
    Prev
    Next
    INDEX
    Explanations

    melting or flowing states

    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
    åĸĺ
    -0.25
    èIJ½åı¶
    -0.20
     ng
    -0.19
    ej
    -0.19
    üz
    -0.19
     MUSIC
    -0.19
    åĩºçĶŁ
    -0.18
    hn
    -0.18
    åīįç½®
    -0.18
    pg
    -0.18
    POSITIVE LOGITS
    èŀį
    0.26
    èŀįåĮĸ
    0.20
    çĨĶ
    0.20
    isper
    0.20
    омеÑĢ
    0.19
    æ´ŀå¯Ł
    0.19
     melting
    0.19
    ibal
    0.19
    orre
    0.19
    -mf
    0.18
    Activations Density 0.023%

    No Known Activations