© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 52654
    Prev
    Next
    INDEX
    Explanations

    sports matches

    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
    覆
    -0.07
    戟
    -0.07
    .Change
    -0.07
    嘴
    -0.07
    污
    -0.07
     Sequence
    -0.07
    (Input
    -0.06
    非常明显
    -0.06
     bern
    -0.06
    кан
    -0.06
    POSITIVE LOGITS
    	as
    0.08
     forKey
    0.07
    agraph
    0.07
     NotImplementedException
    0.07
     página
    0.07
    .='<
    0.07
    =form
    0.07
    一群人
    0.07
    ڣ
    0.07
    0.07
    Activations Density 0.073%

    No Known Activations