© 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 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. 7-RESID-POST-AA
    11. 39023
    Prev
    Next
    INDEX
    Explanations

    vision/provision

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dex
    -0.08
    -required
    -0.07
    uellement
    -0.07
     arose
    -0.07
     kappa
    -0.07
    肯定是
    -0.07
    inned
    -0.07
     Wordpress
    -0.07
    那是
    -0.07
    形状
    -0.07
    POSITIVE LOGITS
     provision
    0.09
    洞
    0.08
    溢价
    0.07
     Spec
    0.07
     TYPO
    0.07
    يوم
    0.07
    招
    0.06
     Resort
    0.06
    INLINE
    0.06
     GetLastError
    0.06
    Activations Density 0.005%

    No Known Activations