INDEX

Explanations

countries

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 especially

-0.29

çī¹ãģ«

-0.27

igner

-0.26

Ð±ÑĢÐ°

-0.26

_UL

-0.25

è¾Ĺè½¬

-0.25

æĮ£æīİ

-0.25

ILog

-0.24

SWG

-0.24

 Barrett

-0.24

POSITIVE LOGITS

Theory

0.29

terior

0.26

 Theory

0.25

gress

0.25

 Reds

0.25

å®ıè§Ĥ

0.25

Ð¾Ð»Ð¶

0.24

obao

0.24

quier

0.23

%@

0.23

Activations Density 0.001%

countries

No Comments

No Known Activations