© 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. 23-RESID-POST-AA
    11. 130066
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _RENDERER
    -0.07
     Show
    -0.07
     Berk
    -0.07
     Lecture
    -0.06
     publié
    -0.06
    瘩
    -0.06
     discover
    -0.06
     seeks
    -0.06
    trash
    -0.06
    plt
    -0.06
    POSITIVE LOGITS
    .getAbsolutePath
    0.08
    atoi
    0.07
    を使った
    0.07
    施肥
    0.06
    RegularExpression
    0.06
    _HEAP
    0.06
    节能环保
    0.06
    思わ
    0.06
     cleanliness
    0.06
     Rolling
    0.06
    Activations Density 0.001%

    No Known Activations