© 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
    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. 129859
    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
     annual
    -0.08
    untu
    -0.08
    西省
    -0.07
    东京
    -0.07
    明显的
    -0.07
    (Common
    -0.07
    繁殖
    -0.07
     pony
    -0.06
     bitte
    -0.06
    -fin
    -0.06
    POSITIVE LOGITS
     themes
    0.07
     ao
    0.07
    IOD
    0.07
    =(
    0.06
    iator
    0.06
     cooldown
    0.06
    ()),
    0.06
     depressed
    0.06
    YPES
    0.06
    ARIABLE
    0.06
    Activations Density 0.001%

    No Known Activations