© 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. 23-RESID-POST-AA
    11. 719
    Prev
    Next
    INDEX
    Explanations

    with

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']↵
    -0.07
     );↵↵↵
    -0.07
    Joseph
    -0.07
    	constructor
    -0.07
    вали
    -0.07
    structure
    -0.07
     Main
    -0.06
    .',↵
    -0.06
    轵
    -0.06
     partnering
    -0.06
    POSITIVE LOGITS
     РФ
    0.09
     forts
    0.08
     winds
    0.07
    APS
    0.07
    _LONG
    0.07
     אברהם
    0.07
    ック
    0.07
    -first
    0.07
     города
    0.07
     huis
    0.07
    Activations Density 0.000%

    No Known Activations