© 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. 25543
    Prev
    Next
    INDEX
    Explanations

    Hiking/travel logs

    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
    _bet
    -0.07
    .pi
    -0.07
    ត
    -0.07
    켄
    -0.07
    ペン
    -0.07
    .prod
    -0.07
    ᴩ
    -0.06
    ingers
    -0.06
    .setPassword
    -0.06
    signature
    -0.06
    POSITIVE LOGITS
    مادة
    0.07
     AAA
    0.06
    مدر
    0.06
    槽
    0.06
    安排
    0.06
     exig
    0.06
     drain
    0.06
     bloc
    0.06
    	obj
    0.06
    使用权
    0.06
    Activations Density 0.057%

    No Known Activations