© 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. 69401
    Prev
    Next
    INDEX
    Explanations

    Code and hashes

    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
    	Address
    -0.08
     varieties
    -0.07
     edges
    -0.07
    放过
    -0.07
    (de
    -0.07
     weigh
    -0.07
    平面
    -0.07
    evento
    -0.07
    Editing
    -0.07
     texto
    -0.07
    POSITIVE LOGITS
    al
    0.09
    [col
    0.08
    il
    0.07
    る
    0.07
     wel
    0.07
    Rol
    0.07
     KL
    0.07
    hl
    0.07
     sul
    0.07
     günümüz
    0.07
    Activations Density 1.288%

    No Known Activations