INDEX

Explanations

pharmaceuticals

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

amburger

-0.28

hol

-0.27

äºĶä¸Ģ

-0.26

ä¸įåħį

-0.26

 chaud

-0.26

æĪĸè®¸

-0.25

 certify

-0.25

Datetime

-0.25

å±±åİ¿

-0.24

hol

-0.24

POSITIVE LOGITS

Vari

0.27

 legion

0.27

Hack

0.26

lude

0.26

ä¸ĩäºĭ

0.25

ä¹ĭæĦı

0.25

Lex

0.24

 solutions

0.24

lein

0.24

å¾Ĵå¼Ł

0.24

Activations Density 0.022%

pharmaceuticals

No Comments

No Known Activations