© 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. 15-RESID-POST-AA
    11. 76810
    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
     capacitor
    -0.07
     urząd
    -0.07
    生活中
    -0.07
    职场
    -0.06
    buat
    -0.06
    _tolerance
    -0.06
    pars
    -0.06
     melakukan
    -0.06
     properly
    -0.06
     Erg
    -0.06
    POSITIVE LOGITS
    _LABEL
    0.07
    -caption
    0.07
    Ⴢ
    0.07
    *)
    0.07
     Dad
    0.07
     ('\
    0.07
    },
↵
↵
    0.07
    LEASE
    0.07
    _upgrade
    0.07
     aslı
    0.07
    Activations Density 0.018%

    No Known Activations