© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92691
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ᐉ
    -0.08
    臃
    -0.07
     Pizza
    -0.07
    Erreur
    -0.07
    之处
    -0.07
    בסופו
    -0.07
    _exclude
    -0.07
     phụ
    -0.06
     nhãn
    -0.06
    NotBlank
    -0.06
    POSITIVE LOGITS
    ὠ
    0.08
    バ
    0.07
    CI
    0.07
     Dig
    0.07
    ギ
    0.07
     Sar
    0.07
    啤
    0.07
     Bali
    0.07
    Closing
    0.07
     Mo
    0.07
    Activations Density 0.077%

    No Known Activations