© 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. 11-RESID-POST-AA
    11. 87622
    Prev
    Next
    INDEX
    Explanations

    letters

    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
    Ṩ
    -0.08
    폅
    -0.07
    ᴇ
    -0.07
    たい
    -0.07
    Tre
    -0.07
    مر
    -0.06
    _DROP
    -0.06
    aines
    -0.06
    كبر
    -0.06
    zens
    -0.06
    POSITIVE LOGITS
     retVal
    0.08
    撤
    0.07
     Editorial
    0.07
    𝇚
    0.07
     TCL
    0.07
     writing
    0.07
     publicly
    0.07
    无敌
    0.07
     по
    0.07
    党政
    0.07
    Activations Density 0.012%

    No Known Activations