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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 86147
    Prev
    Next
    INDEX
    Explanations

    looking in mirrors

    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
    ModelProperty
    -0.09
     FileType
    -0.07
    ܥ
    -0.07
     Plains
    -0.07
    infile
    -0.07
    Italian
    -0.06
    AspNet
    -0.06
    エ
    -0.06
    𦭜
    -0.06
     paternal
    -0.06
    POSITIVE LOGITS
    łó
    0.07
    _SLOT
    0.07
    _resolution
    0.07
    	this
    0.07
    äd
    0.07
    _AD
    0.07
     GOLD
    0.07
    .pr
    0.07
    が始ま
    0.07
     revealing
    0.07
    Activations Density 0.017%

    No Known Activations