© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 79092
    Prev
    Next
    INDEX
    Explanations

    able

    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
    hide
    -0.07
    iets
    -0.07
    Arguments
    -0.07
    KT
    -0.07
    𬶟
    -0.07
    [to
    -0.06
    (compare
    -0.06
    eller
    -0.06
     frees
    -0.06
    itz
    -0.06
    POSITIVE LOGITS
    	res
    0.08
    .InputStream
    0.08
    )"↵↵
    0.08
     nutritious
    0.07
     res
    0.07
     arrival
    0.07
    果实
    0.07
    配方
    0.07
     الدم
    0.07
     dipped
    0.07
    Activations Density 0.020%

    No Known Activations