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. 15-RESID-POST-AA
    6. 1508
    Prev
    Next
    INDEX
    Explanations

    Shortened words or code fragments

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confuse
    -0.07
    鲹
    -0.07
    愐
    -0.07
    对话
    -0.07
    �
    -0.07
    Checking
    -0.07
    .do
    -0.06
    _As
    -0.06
     widen
    -0.06
    En
    -0.06
    POSITIVE LOGITS
     safety
    0.07
    authors
    0.07
    	create
    0.07
     antiqu
    0.07
     Saf
    0.07
    ISTR
    0.07
     '['
    0.06
    структор
    0.06
    paragraph
    0.06
     Nacional
    0.06
    Activations Density 0.443%

    No Known Activations