INDEX

Explanations

possibility

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

oses

-0.25

æ¹ĺ

-0.25

cul

-0.25

 Ð´Ð¾Ð³

-0.24

esc

-0.24

æŀ¢

-0.24

Es

-0.24

 Enterprises

-0.24

 cracks

-0.24

dcc

-0.24

POSITIVE LOGITS

ipsoid

0.26

åĲĦæĸ¹éĿ¢

0.25

 attest

0.25

pery

0.24

ä¸īä½įä¸Ģä½ĵ

0.24

 gloss

0.24

geries

0.24

 opin

0.23

 shape

0.23

(::

0.23

Activations Density 0.001%

possibility

No Comments

No Known Activations