© 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. 5797
    Prev
    Next
    INDEX
    Explanations

    root calculations

    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
     Texans
    -0.08
    らず
    -0.07
    Nach
    -0.07
    _ary
    -0.07
    Des
    -0.07
    usi
    -0.07
    	icon
    -0.07
     unas
    -0.07
     el
    -0.07
    不满
    -0.07
    POSITIVE LOGITS
    إجراءات
    0.07
     programmed
    0.07
     Steelers
    0.07
    𝕺
    0.07
     серь
    0.07
     darm
    0.07
     PhD
    0.06
     downt
    0.06
    .Transfer
    0.06
     buried
    0.06
    Activations Density 0.005%

    No Known Activations