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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 130146
    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
     стол
    -0.08
    🎨
    -0.07
     Techniques
    -0.07
    。。
    -0.07
    (style
    -0.07
    sts
    -0.07
     Strateg
    -0.07
     THEN
    -0.07
     ActionTypes
    -0.07
    BagConstraints
    -0.06
    POSITIVE LOGITS
    ไข
    0.07
     trapped
    0.07
     fullPath
    0.07
    中国
    0.07
    離開
    0.07
     hayat
    0.07
    代言
    0.07
    暖心
    0.07
    聚会
    0.07
    成長
    0.06
    Activations Density 0.091%

    No Known Activations