INDEX

Explanations

lope

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

prend

-0.26

/to

-0.26

prising

-0.26

haps

-0.26

 Passing

-0.25

-bs

-0.25

Ã©ny

-0.24

.algorithm

-0.24

Ã¥n

-0.24

erea

-0.23

POSITIVE LOGITS

 versch

0.28

æĥ³ä¸įåĪ°

0.26

 substitutions

0.25

 upro

0.25

ç³»

0.25

åıĺåĮĸ

0.25

 alternative

0.24

 substit

0.24

alternative

0.24

è¶ħ

0.24

Activations Density 0.783%

lope

No Comments

No Known Activations