INDEX

Explanations

identifiers or code fragments

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

abh

-0.30

 tapped

-0.28

tap

-0.27

favor

-0.26

åĬ¨

-0.26

åĽ½å¤ĸ

-0.26

onyms

-0.26

pow

-0.25

favorites

-0.25

 favor

-0.25

POSITIVE LOGITS

æľĢåĲİä¸Ģ

0.30

 birth

0.28

çļĦæľĢåĲİä¸Ģ

0.28

iani

0.26

åĩºçĶŁ

0.26

é©¾çħ§

0.25

ophone

0.25

 legislature

0.25

 Franklin

0.25

è¯Ŀ

0.24

Activations Density 0.783%

identifiers or code fragments

No Known Activations