INDEX

Explanations

Mixed content (code, math, text)

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

äºĶå¤§

-0.26

å¹¿

-0.26

 unsupported

-0.25

à¤ĺ

-0.25

quis

-0.25

 narrow

-0.25

 supported

-0.24

 Berger

-0.24

 even

-0.24

ç¬¬ä¸Ģå®¶

-0.24

POSITIVE LOGITS

 Rooney

0.33

istani

0.30

ç¨³

0.27

åĩ½

0.26

Replacement

0.26

TES

0.26

enstein

0.25

_exempt

0.25

stin

0.24

_TM

0.24

Activations Density 0.041%

Mixed content (code, math, text)

No Comments

No Known Activations