Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 44199
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vamp
    -0.07
    ספטמ
    -0.07
    vehicle
    -0.07
    Nh
    -0.07
    ighton
    -0.07
    ன
    -0.07
    別人
    -0.07
    igers
    -0.07
     "),↵
    -0.07
    ecided
    -0.07
    POSITIVE LOGITS
    نتائ
    0.07
     Curso
    0.07
    STRACT
    0.07
    "The
    0.07
    快捷
    0.06
     async
    0.06
    ()=>
    0.06
    效果
    0.06
    	void
    0.06
     utiliz
    0.06
    Activations Density 0.399%

    No Known Activations