© 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. 15-RESID-POST-AA
    11. 20707
    Prev
    Next
    INDEX
    Explanations

    Text normalization

    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
     הנוכ
    -0.07
    \Resources
    -0.07
     Lia
    -0.06
     concl
    -0.06
    콕
    -0.06
    	Base
    -0.06
    Reservation
    -0.06
     Dien
    -0.06
    +"]
    -0.06
    >{{$
    -0.06
    POSITIVE LOGITS
     BATCH
    0.07
    𝘏
    0.07
     Rug
    0.07
    弟兄
    0.07
    פית
    0.06
    Dirty
    0.06
    olly
    0.06
    comput
    0.06
     transplant
    0.06
    ــ
    0.06
    Activations Density 0.035%

    No Known Activations