© 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. 116753
    Prev
    Next
    INDEX
    Explanations

    Instructions or repair

    np_max-act · gemini-2.0-flash
    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
     established
    -0.08
    قابل
    -0.07
    emann
    -0.07
    Texto
    -0.06
    -elected
    -0.06
                  ↵
    -0.06
     negó
    -0.06
    ♎
    -0.06
     doivent
    -0.06
    這些
    -0.06
    POSITIVE LOGITS
     Upon
    0.08
     пут
    0.08
    -front
    0.08
    >::
    0.08
     bedtime
    0.07
    MAIL
    0.07
    Drawing
    0.07
     род
    0.07
     fallout
    0.07
     Foot
    0.07
    Activations Density 0.284%

    No Known Activations