© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 23783
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    内の
    -0.09
    irse
    -0.08
    鼓励
    -0.07
    create
    -0.07
    nev
    -0.07
     Document
    -0.07
    ଽ
    -0.07
    湖南省
    -0.07
    شار
    -0.07
     Thảo
    -0.07
    POSITIVE LOGITS
     tek
    0.08
    贫困人口
    0.07
     wealthiest
    0.07
    amel
    0.07
    去世
    0.07
    ﭝ
    0.07
    $time
    0.07
    полнить
    0.06
    	x
    0.06
     пло
    0.06
    Activations Density 0.049%

    No Known Activations