INDEX

Explanations

ebooks

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

Ã¼m

-0.32

-Smith

-0.27

èī¯

-0.26

 mild

-0.25

 lied

-0.25

ailles

-0.25

-Sep

-0.24

ody

-0.23

stein

-0.23

å®£åĳĬ

-0.23

POSITIVE LOGITS

çļĦè®¤çŁ¥

0.27

htt

0.26

æ¼±

0.26

çļĦè®¤è¯Ĩ

0.26

 Institutional

0.25

HttpResponse

0.25

 traff

0.25

Ð³Ð°Ð»

0.24

circ

0.24

 ASAP

0.24

Activations Density 0.002%

ebooks

No Comments

No Known Activations