© 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. 89627
    Prev
    Next
    INDEX
    Explanations

    legal texts

    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
    -sectional
    -0.07
    .nextSibling
    -0.07
    -ng
    -0.07
     Điểm
    -0.07
    byte
    -0.07
     Gallup
    -0.07
     Lup
    -0.07
    伶
    -0.07
    预订
    -0.07
     Buckley
    -0.07
    POSITIVE LOGITS
     smoker
    0.07
    =w
    0.07
    #$
    0.07
    ==$
    0.07
    hat
    0.07
    ERICA
    0.06
    ;if
    0.06
    ٶ
    0.06
     City
    0.06
    heel
    0.06
    Activations Density 0.079%

    No Known Activations