© 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. 23475
    Prev
    Next
    INDEX
    Explanations

    shirt

    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
     StringSplitOptions
    -0.08
     communion
    -0.08
    تصريح
    -0.08
    截止
    -0.07
    _OscInitStruct
    -0.07
     pami
    -0.07
    其它问题
    -0.07
    �
    -0.07
     possessing
    -0.07
    洧
    -0.07
    POSITIVE LOGITS
     estate
    0.08
    :text
    0.07
    ガイ
    0.06
     Nacht
    0.06
     Atl
    0.06
     Vanguard
    0.06
    었습니다
    0.06
     woes
    0.06
     últ
    0.06
    兩個
    0.06
    Activations Density 0.006%

    No Known Activations