© 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. 23867
    Prev
    Next
    INDEX
    Explanations

    it

    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
    完整热
    -0.07
     satisfies
    -0.07
     Wilson
    -0.07
    ၊
    -0.07
    .ff
    -0.07
     î
    -0.07
    _PROD
    -0.07
    ystate
    -0.07
    ',//
    -0.07
    เธ
    -0.07
    POSITIVE LOGITS
    因为它
    0.07
    广大
    0.07
    reements
    0.07
    层层
    0.07
     tới
    0.06
    вшис
    0.06
     polít
    0.06
    썻
    0.06
     böyle
    0.06
    bear
    0.06
    Activations Density 0.040%

    No Known Activations