© 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. 11-RESID-POST-AA
    11. 61511
    Prev
    Next
    INDEX
    Explanations

    sports starting games

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ра�
    -0.08
    齑
    -0.07
    iciary
    -0.07
    山西省
    -0.07
    这样说
    -0.07
    資金
    -0.07
    ListGroup
    -0.07
     마지
    -0.07
    jspb
    -0.07
    .XtraLayout
    -0.06
    POSITIVE LOGITS
    rypton
    0.07
    press
    0.07
    NAL
    0.07
    /back
    0.07
    	global
    0.06
    ena
    0.06
    渡
    0.06
    孕
    0.06
    testimonial
    0.06
    col
    0.06
    Activations Density 0.012%

    No Known Activations