INDEX

Explanations

seem/feel

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stadt

-0.28

VEC

-0.27

MC

-0.26

WC

-0.25

His

-0.24

nye

-0.24

mong

-0.24

MC

-0.24

 HVAC

-0.24

 Valle

-0.24

POSITIVE LOGITS

hek

0.30

preter

0.29

eref

0.27

æ¢³

0.27

ertype

0.26

 Kata

0.26

irl

0.25

å««

0.24

Disp

0.24

dere

0.24

Activations Density 0.791%

seem/feel

No Comments

No Known Activations