Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 60645
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     predicts
    -0.08
    面条
    -0.08
    Notify
    -0.07
    rod
    -0.07
    GRP
    -0.07
     conducts
    -0.07
     ראיתי
    -0.07
    امت
    -0.07
    エ
    -0.06
     existe
    -0.06
    POSITIVE LOGITS
     التش
    0.07
    ἕ
    0.07
     결
    0.07
    ᩉ
    0.07
    格尔
    0.07
    #error
    0.07
    Peak
    0.07
     Wrapper
    0.06
     bü
    0.06
    (kwargs
    0.06
    Activations Density 0.042%

    No Known Activations