INDEX

Explanations

medical/scientific abstracts

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

vw

-0.28

æ±Ĥå©ļ

-0.28

é¾Ī

-0.27

çĪ¶

-0.26

è±ķ

-0.26

omination

-0.26

gran

-0.25

é³į

-0.25

variant

-0.24

iena

-0.24

POSITIVE LOGITS

edList

0.29

sap

0.27

 sscanf

0.26

 densities

0.26

RATE

0.26

arlo

0.25

ations

0.25

 znale

0.25

 lá»±c

0.25

lightly

0.24

Activations Density 0.020%

medical/scientific abstracts

No Comments

No Known Activations