INDEX

Explanations

varied online text excerpts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Google

-0.29

uali

-0.28

 google

-0.27

 stav

-0.27

çĻ¾åº¦

-0.26

Google

-0.25

èĩªæĿĢ

-0.25

_google

-0.25

è°¯

-0.24

åĵ²

-0.24

POSITIVE LOGITS

 cable

0.27

Gig

0.26

-output

0.26

æĭ¦

0.25

ç¼´

0.25

 lined

0.25

output

0.24

AAAAAAAA

0.24

ipt

0.24

 illuminated

0.24

Activations Density 0.002%

varied online text excerpts

No Comments

No Known Activations