INDEX

Explanations

Code/technical identifiers

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

çµ²

-0.27

 boyc

-0.27

 Ð¾Ð´Ð½Ð¾

-0.26

irc

-0.26

#:

-0.25

_proto

-0.25

ois

-0.25

äºĴ

-0.25

Ð¿ÑĥÑģÐºÐ°

-0.25

odes

-0.24

POSITIVE LOGITS

.assign

0.33

-pattern

0.32

æĹ§

0.28

çŃ²

0.28

quake

0.27

yh

0.26

ìĿ¸ìĿ´

0.26

flare

0.25

æŁĦ

0.25

ceu

0.25

Activations Density 0.002%

Code/technical identifiers

No Comments

No Known Activations