© 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. 19-RESID-POST-AA
    11. 70175
    Prev
    Next
    INDEX
    Explanations

    say "ers" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Missile
    -0.08
    _ONCE
    -0.07
     Todd
    -0.07
    有幸
    -0.07
     avi
    -0.07
    _adc
    -0.07
    .BLUE
    -0.07
    🌸
    -0.07
    特种
    -0.07
    Informe
    -0.07
    POSITIVE LOGITS
    	version
    0.07
    essional
    0.07
    too
    0.07
    resh
    0.07
     trail
    0.07
    _don
    0.06
    泽
    0.06
    יט
    0.06
     fora
    0.06
    potential
    0.06
    Activations Density 0.016%

    No Known Activations