© 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. 15-RESID-POST-AA
    6. 42015
    Prev
    Next
    INDEX
    Explanations

    CPU frequency code identifiers

    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
     genders
    -0.07
    תיא
    -0.07
     -------------------------------------------------------------------------
    -0.07
    行车
    -0.07
    Props
    -0.07
    詩
    -0.06
    	
    ↵
    ↵
    -0.06
    党员干部
    -0.06
     gj
    -0.06
    etrize
    -0.06
    POSITIVE LOGITS
    ustralia
    0.07
     appeal
    0.06
    	    		
    0.06
    羊毛
    0.06
    htub
    0.06
    체
    0.06
    .AL
    0.06
     Bölge
    0.06
    Progress
    0.06
     setbacks
    0.06
    Activations Density 0.000%

    No Known Activations