© 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. 19-RESID-POST-AA
    11. 8643
    Prev
    Next
    INDEX
    Explanations

    Technical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wilt
    -0.07
     нельз
    -0.07
    /right
    -0.07
    湟
    -0.07
    assertSame
    -0.06
    	In
    -0.06
     Agu
    -0.06
     NAMES
    -0.06
    wel
    -0.06
    ترت
    -0.06
    POSITIVE LOGITS
     presidente
    0.07
     whistleblower
    0.07
     storyline
    0.07
     proposals
    0.07
     Kết
    0.07
    产生
    0.07
     מידע
    0.07
    传闻
    0.07
     Devon
    0.07
    _odd
    0.07
    Activations Density 0.001%

    No Known Activations