© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 76287
    Prev
    Next
    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    实际情况
    -0.08
     legend
    -0.07
    	final
    -0.07
     shar
    -0.07
     dispatched
    -0.07
     fakt
    -0.07
    telegram
    -0.07
     тем
    -0.07
     ge
    -0.06
     thirsty
    -0.06
    POSITIVE LOGITS
     Cedar
    0.08
     OCD
    0.06
    ㌔
    0.06
    #$
    0.06
     *));↵
    0.06
    剥离
    0.06
    也让
    0.06
    已经超过
    0.06
     nrows
    0.06
    ltr
    0.06
    Activations Density 0.004%

    No Known Activations