INDEX

Explanations

first person narrative

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

ä½¿çĶ¨èĢħæĪĸ

-0.27

ÑĩÐ¸Ð½

-0.27

Ð»ÐµÐ¶Ð°

-0.26

notated

-0.25

ening

-0.25

æĥ³æī¾

-0.25

èĩĮ

-0.25

Slinky

-0.24

åľ¨çİ©å®¶

-0.23

 greatly

-0.23

POSITIVE LOGITS

 prose

0.29

 autos

0.28

ç»§

0.27

é²ģ

0.26

autos

0.26

æĢİä¹Īåģļ

0.25

éĩİ

0.25

ÑĢÐ¾ÑģÑģ

0.25

 interior

0.25

ader

0.25

Activations Density 0.018%

first person narrative

No Comments

No Known Activations