INDEX

Explanations

Document snippets/extractions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istent

-0.29

æ²Ł

-0.28

-human

-0.27

éĢĬ

-0.24

 Roger

-0.24

è¯´è¿ĩ

-0.24

å·ŀå¸Ĥ

-0.23

ieme

-0.23

 sorted

-0.23

illon

-0.23

POSITIVE LOGITS

Women

0.28

å¤´ä¸Ĭ

0.28

akh

0.28

ORN

0.26

ARN

0.26

 Women

0.24

shape

0.24

 shape

0.24

 Origin

0.23

æĬ¥ä¸ļ

0.23

Activations Density 26.477%

Document snippets/extractions

No Comments

No Known Activations