© 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. 11-RESID-POST-AA
    11. 25501
    Prev
    Next
    INDEX
    Explanations

    cheesy

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nuest
    -0.07
     broadcasts
    -0.06
     gains
    -0.06
    병
    -0.06
     SSD
    -0.06
    לימ
    -0.06
    𝒅
    -0.06
     prise
    -0.06
    🛵
    -0.06
    ağ
    -0.06
    POSITIVE LOGITS
     mocking
    0.07
    urous
    0.07
    ﭷ
    0.07
    typings
    0.07
    (resolve
    0.07
     shock
    0.07
    拜访
    0.07
    parentNode
    0.07
    直到
    0.07
    反
    0.07
    Activations Density 0.010%

    No Known Activations