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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 29813
    Prev
    Next
    INDEX
    Explanations

    code files

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	user
    -0.08
    	selected
    -0.08
    �
    -0.07
    都没
    -0.07
     DBNull
    -0.07
    	cur
    -0.07
    毛孔
    -0.07
    imin
    -0.06
    腿部
    -0.06
    (bottom
    -0.06
    POSITIVE LOGITS
    ༄
    0.07
    illé
    0.07
    ético
    0.07
    외
    0.07
    筛查
    0.07
    朝阳
    0.07
    Uri
    0.07
    _cleanup
    0.07
     realities
    0.07
    lua
    0.07
    Activations Density 0.003%

    No Known Activations