INDEX

Explanations

code

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

åľĪ

-0.30

uture

-0.28

verbatim

-0.26

oir

-0.26

leck

-0.26

 Compound

-0.25

èĬ½

-0.25

å¼ĢèįĴ

-0.25

road

-0.25

 propag

-0.25

POSITIVE LOGITS

è¿©

0.28

|"

0.27

ersh

0.26

uve

0.26

Rap

0.25

iks

0.25

ãģĳ

0.25

<",

0.25

.Xr

0.25

egr

0.24

Activations Density 0.002%

code

No Comments

No Known Activations