INDEX

Explanations

obesity

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

ouble

-0.28

icles

-0.27

ÉĲ

-0.27

åŀĴ

-0.26

ugar

-0.26

unya

-0.25

urity

-0.25

iamond

-0.25

tra

-0.25

-through

-0.24

POSITIVE LOGITS

TMP

0.27

FU

0.26

FU

0.26

rh

0.26

å§ĵ

0.25

ril

0.25

riv

0.25

 vendors

0.25

BED

0.24

eph

0.24

Activations Density 0.001%

obesity

No Comments

No Known Activations