INDEX

Explanations

disease activity

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

iline

-0.36

æ³ķå¾ĭè§Ħå®ļ

-0.27

azzi

-0.27

åľ¨çº¿

-0.26

ochen

-0.25

ME

-0.25

 Ø§ÙĦØªÙĤ

-0.25

 newArr

-0.25

hay

-0.24

æĸ°å¨ĺ

-0.24

POSITIVE LOGITS

æ¸º

0.27

ACCEPT

0.25

 ASAP

0.25

çĶ¨å¾®ä¿¡

0.25

mug

0.25

Zero

0.24

avourite

0.24

Indented

0.24

ingular

0.24

 Huffman

0.24

Activations Density 0.002%

disease activity

No Comments

No Known Activations