INDEX

Explanations

first

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DownList

-0.26

 Tiger

-0.25

æĥ³è¿ĩ

-0.25

 Ã¶l

-0.25

éľģ

-0.25

 thiá»ĩn

-0.24

 Herc

-0.24

inker

-0.24

 tolerance

-0.23

 plane

-0.23

POSITIVE LOGITS

 scram

0.27

æĪĳä»¬çļĦ

0.26

æ®Ĭ

0.26

èŃ¬

0.26

çīĮ

0.25

 Ð¿ÑĢÐµÐ¸Ð¼

0.25

 familiar

0.24

ano

0.24

Fam

0.24

ication

0.24

Activations Density 0.002%

first

No Comments

No Known Activations