© 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. 76364
    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
    .”↵↵↵↵
    -0.07
     items
    -0.07
     bud
    -0.06
    内涵
    -0.06
    둠
    -0.06
    Obsolete
    -0.06
    esper
    -0.06
    Hide
    -0.06
    rename
    -0.06
     redeem
    -0.06
    POSITIVE LOGITS
    髻
    0.07
     equal
    0.07
     Appl
    0.07
     sức
    0.07
    iert
    0.07
     Curl
    0.06
    怆
    0.06
    ,column
    0.06
    Optimizer
    0.06
     sacr
    0.06
    Activations Density 0.012%

    No Known Activations