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. 57216
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sons
    -0.09
    Img
    -0.07
    מוש
    -0.07
    谤
    -0.07
    streams
    -0.07
    箱
    -0.07
    lobs
    -0.07
     Tube
    -0.07
     Watson
    -0.07
    shiv
    -0.06
    POSITIVE LOGITS
     полностью
    0.07
    更换
    0.07
    💺
    0.07
    _compat
    0.07
     impartial
    0.07
    	report
    0.07
     FETCH
    0.07
     הפר
    0.07
     unpredict
    0.07
    iliary
    0.07
    Activations Density 0.191%

    No Known Activations