© 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. 521
    Prev
    Next
    INDEX
    Explanations

    a sense of improvement

    np_max-act-logits · gemini-2.0-flash
    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
     sings
    -0.07
    市場
    -0.07
    شر
    -0.07
    -base
    -0.07
     biển
    -0.07
    沪指
    -0.07
    等多种
    -0.07
     vowed
    -0.07
    Genesis
    -0.07
     العم
    -0.07
    POSITIVE LOGITS
     }}↵↵
    0.08
     overlooking
    0.07
    
    0.07
     strategist
    0.07
     ToDo
    0.07
    FULL
    0.07
    queryString
    0.07
    罚款
    0.06
     EVER
    0.06
    ;}
    0.06
    Activations Density 0.131%

    No Known Activations