INDEX

Explanations

Existence and questions

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

äºĨä¸Ģåľº

-0.26

Bid

-0.25

VS

-0.25

ä¸ĵä¸ļçŁ¥è¯Ĩ

-0.25

Bid

-0.24

æĿĥ

-0.23

FD

-0.23

 âĩ

-0.23

strength

-0.23

ç¬Ķ

-0.23

POSITIVE LOGITS

çıŀ

0.29

eturn

0.29

_Framework

0.27

_framework

0.27

enerative

0.26

_IMPORTED

0.26

 purs

0.26

 Ð´Ð°Ð»

0.25

é«ĺå³°

0.25

utherford

0.25

Activations Density 0.006%

Existence and questions

No Comments

No Known Activations