INDEX

Explanations

white

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 personally

-0.30

 Ð»Ð¸ÑĩÐ½Ð¾

-0.29

 Epstein

-0.28

akest

-0.28

ouch

-0.28

uko

-0.28

fell

-0.26

opes

-0.25

arness

-0.25

 aloud

-0.25

POSITIVE LOGITS

è§£åĨ³æĸ¹æ¡Ī

0.26

 crap

0.26

å¢ĥçķĮ

0.25

 guesses

0.25

ex

0.25

å¢ĥåĨħ

0.24

dig

0.24

åĪĳ

0.24

dig

0.24

lox

0.24

Activations Density 0.008%

white

No Comments

No Known Activations